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. 16-GEMMASCOPE-RES-16K
    6. 16136
    Prev
    Next
    INDEX
    Explanations

    specific numeric patterns and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithMany
    -0.56
    tonode
    -0.53
    ingroup
    -0.47
     beginnetje
    -0.47
    vées
    -0.47
    setViewName
    -0.46
    eses
    -0.45
     conventional
    -0.44
    __((
    -0.44
     normalize
    -0.44
    POSITIVE LOGITS
    viembre
    0.63
    BeginContext
    0.63
     AttributeSet
    0.62
     useDispatch
    0.62
    AddTagHelper
    0.61
    SourceChecksum
    0.61
    Према
    0.59
    Ligações
    0.58
    archiviato
    0.57
    JSONException
    0.56
    Activations Density 0.164%

    No Known Activations