© 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. 394
    Prev
    Next
    INDEX
    Explanations

    elements related to coding operations and data management in programming

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

    method calls or function invocations with dot notation followed by parentheses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     InputDecoration
    -0.68
    AccessorTable
    -0.62
    ConverterFactory
    -0.57
    MemoryWarning
    -0.57
    Filmografie
    -0.56
    tonsoft
    -0.55
    fjspx
    -0.54
     queſta
    -0.53
     CYTHON
    -0.53
    tisgarh
    -0.52
    POSITIVE LOGITS
    Mr
    0.52
     Mr
    0.51
     ihn
    0.43
     him
    0.42
    (@"%@",
    0.40
     conoció
    0.39
     conoci
    0.37
     따라
    0.36
     sitä
    0.36
    copyOf
    0.36
    Activations Density 0.403%

    No Known Activations