Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4157
    Prev
    Next
    INDEX
    Explanations

    chemical substances and their properties related to microbial and medicinal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gk
    -0.80
    CK
    -0.78
     ck
    -0.78
     CK
    -0.77
     LK
    -0.75
     pk
    -0.74
     GK
    -0.70
     jk
    -0.70
     RK
    -0.70
     fk
    -0.69
    POSITIVE LOGITS
     Keep
    0.72
    Keep
    0.71
    Knowledge
    0.68
    KEEP
    0.67
     Kind
    0.66
     Kids
    0.66
     Knowledge
    0.65
     Know
    0.65
    AutoField
    0.64
     Killing
    0.63
    Activations Density 0.277%

    No Known Activations