© 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. 5979
    Prev
    Next
    INDEX
    Explanations

    phrases that denote a sequence of items or issues

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

    ordinal numbers and their associated descriptive phrases (like "The first is...", "The second is...").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     estekak
    -0.52
    irmingham
    -0.45
    erevan
    -0.41
     Malt
    -0.39
    hydrogenase
    -0.39
    褫
    -0.39
     Accountant
    -0.39
    Strawberry
    -0.38
     diable
    -0.38
     sterilized
    -0.38
    POSITIVE LOGITS
    ⤹
    0.56
    writeFieldEnd
    0.55
     CreateTagHelper
    0.53
    RenderAtEndOf
    0.51
    AndEndTag
    0.47
     HasFactory
    0.47
     is
    0.45
    expandindo
    0.42
     autorytatywna
    0.40
    Décès
    0.40
    Activations Density 0.272%

    No Known Activations