© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8932
    Prev
    Next
    INDEX
    Explanations

    frequently occurring conjunctions and articles in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.76
     referenties
    -0.71
     mergeFrom
    -0.58
    <bos>
    -0.55
    nieuw
    -0.55
    uxxxx
    -0.54
    AccessorTable
    -0.53
     jinak
    -0.53
    '])){
    -0.51
     виправивши
    -0.50
    POSITIVE LOGITS
    󠁧
    0.64
    ValueGenerated
    0.63
    RuleContext
    0.60
    HtmlAttribute
    0.59
     IBOutlet
    0.58
    GHIJKLM
    0.58
    ൂ
    0.57
    сій
    0.54
    mtrl
    0.54
    πω
    0.53
    Activations Density 1.012%

    No Known Activations