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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 16020
    Prev
    Next
    INDEX
    Explanations

    concepts related to rules, prevention, and structured processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fer
    -0.49
     C
    -0.47
    忍
    -0.45
     Sy
    -0.44
     Flo
    -0.42
     Pas
    -0.42
     fer
    -0.40
    richt
    -0.40
    urin
    -0.40
     Investig
    -0.39
    POSITIVE LOGITS
    :+:
    0.82
    AddTagHelper
    0.76
    raszamy
    0.69
    +#+#
    0.69
     ―――――
    0.67
     FormGroup
    0.65
    )";
    0.64
     himo
    0.64
    WithIOException
    0.63
     Diretto
    0.63
    Activations Density 0.618%

    No Known Activations