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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 9709
    Prev
    Next
    INDEX
    Explanations

    terms related to "communication" or "com" as a prefix in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.88
    ★☆
    -0.75
    EndTag
    -0.72
     برانيه
    -0.71
    UVWXYZ
    -0.69
    WebControls
    -0.69
    bnf
    -0.69
    #+#
    -0.69
    Portail
    -0.68
     HasFactory
    -0.68
    POSITIVE LOGITS
     COM
    1.31
    COM
    1.22
    Com
    1.20
     Com
    1.18
     KOM
    1.16
     COMM
    1.09
     Comm
    1.04
     Kom
    1.03
    Kom
    1.02
    KOM
    1.01
    Activations Density 0.063%

    No Known Activations