© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15656
    Prev
    Next
    INDEX
    Explanations

    references to materials or components in a context of description or specification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    relative pronouns like "which" and "whom" that introduce clauses referring to previously mentioned objects.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ₂+
    -0.46
     Berufs
    -0.45
    しゃれ
    -0.43
     مشين
    -0.41
    yyb
    -0.41
     chrétien
    -0.40
    但不
    -0.40
     Pfarr
    -0.39
    swire
    -0.39
     BT
    -0.39
    POSITIVE LOGITS
    Whom
    0.63
    whom
    0.60
     estekak
    0.60
     whom
    0.57
    where
    0.57
     noDo
    0.57
    wherein
    0.55
     whereof
    0.54
    Where
    0.53
    which
    0.52
    Activations Density 0.090%

    No Known Activations