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. 18-GEMMASCOPE-RES-16K
    6. 10662
    Prev
    Next
    INDEX
    Explanations

    instances of agreement or consensus among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.67
     "..\..\
    -0.67
    :+:
    -0.58
     NavController
    -0.58
     виправивши
    -0.55
     ModelExpression
    -0.54
     dal
    -0.54
     censiti
    -0.54
     "..\..\..\
    -0.52
    hawar
    -0.52
    POSITIVE LOGITS
    Agre
    0.91
     Disagree
    0.89
     Agreements
    0.79
     agreements
    0.79
     Agre
    0.78
     Agree
    0.78
     AGRE
    0.76
    agree
    0.71
     agrees
    0.70
     disagree
    0.69
    Activations Density 0.175%

    No Known Activations