© 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. 5-GEMMASCOPE-RES-16K
    11. 10878
    Prev
    Next
    INDEX
    Explanations

    multiple opening parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulo
    -0.49
    </strong>
    -0.48
    >>>
    -0.48
     "__
    -0.47
     vuông
    -0.47
    öv
    -0.46
     virtu
    -0.45
     Switch
    -0.45
    ";
    -0.45
    qui
    -0.44
    POSITIVE LOGITS
     kaynağından
    1.18
    Personendaten
    1.13
    enumii
    0.96
    AndEndTag
    0.90
     مُعرِّف
    0.88
     ModelExpression
    0.86
    //
    0.82
    tagHelperRunner
    0.81
     Commencez
    0.81
    sieur
    0.79
    Activations Density 0.016%

    No Known Activations