© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10423
    Prev
    Next
    INDEX
    Explanations

    JavaScript or programming-related function calls and data handling operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numeric literals and their operations in programming code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    variable or object property access in programming code, particularly when indexing arrays or accessing object members.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    code tokens from programming snippets, especially short variable identifiers and DOM/event-related property or method accesses.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.63
    abstractmethod
    -0.60
    "}>
    -0.53
    ViewInit
    -0.51
    .")]
    -0.50
    }*/
    
    -0.50
    }*/
    -0.50
    vatar
    -0.49
    .)}
    -0.49
    页面存档备份
    -0.49
    POSITIVE LOGITS
    posedge
    0.44
    ();
    0.41
    [];
    0.38
    ;
    0.38
    MessageState
    0.34
    progress
    0.32
     createSlice
    0.32
    ()?;
    0.32
    gráfica
    0.30
     tilbage
    0.30
    Activations Density 0.442%

    No Known Activations