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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 14067
    Prev
    Next
    INDEX
    Explanations

    references to studies or reports involving statistical analysis and data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̍t
    -0.59
    matchCondition
    -0.58
     كومونز
    -0.58
    存于互联网档案馆
    -0.57
    expandindo
    -0.56
    EndProject
    -0.53
     Orrell
    -0.52
    SerializedSize
    -0.52
     kaarangay
    -0.52
    sidemargin
    -0.51
    POSITIVE LOGITS
    MSA
    0.90
    SPA
    0.87
     MSA
    0.85
    CTA
    0.83
    TSA
    0.80
    OMA
    0.80
     MCA
    0.80
    LLA
    0.79
     DCA
    0.79
    SCA
    0.78
    Activations Density 0.752%

    No Known Activations