© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4833
    Prev
    Next
    INDEX
    Explanations

    mathematical problems and questions involving factors and multiples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,:);
    -1.01
     ―――――
    -1.01
    Personensuche
    -0.88
     himo
    -0.86
     Efq
    -0.85
    SPATH
    -0.85
     ་་
    -0.84
     NDEBUG
    -0.82
    دانشنامهٔ
    -0.80
    Vea
    -0.80
    POSITIVE LOGITS
    3
    1.15
    5
    1.07
    4
    1.04
     three
    0.91
    6
    0.91
    0
    0.86
    2
    0.86
    three
    0.85
     Tri
    0.81
     tri
    0.80
    Activations Density 1.015%

    No Known Activations