© 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. 3-GEMMASCOPE-RES-16K
    11. 9919
    Prev
    Next
    INDEX
    Explanations

    phrases relating to hierarchical structures or divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     QLabel
    -0.48
    Portale
    -0.46
    CrossOrigin
    -0.43
    titutions
    -0.40
     كمان
    -0.40
     zove
    -0.40
     thứ
    -0.39
    frid
    -0.39
     Cle
    -0.39
    第
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.98
    RenderAtEndOf
    0.87
    ]")]
    0.82
    IsContent
    0.75
    enterOuterAlt
    0.74
    Obrázky
    0.71
    `;
    0.71
     insuffisamment
    0.71
     arşivlendi
    0.70
     Bioaccumulative
    0.70
    Activations Density 0.414%

    No Known Activations