© 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. 6244
    Prev
    Next
    INDEX
    Explanations

    concepts related to social critique and commentary

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

    prepositional phrases involving transition or movement, particularly phrases with "to" that suggest progression or change.

    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
    enumi
    -0.60
    licherweise
    -0.48
    锢
    -0.44
     useStyles
    -0.44
     whoſe
    -0.44
     alber
    -0.43
     hindurch
    -0.43
     Públicas
    -0.43
    aneers
    -0.42
    wnież
    -0.42
    POSITIVE LOGITS
    addGap
    0.64
    ]='\
    0.56
    zA
    0.56
     sitesinde
    0.53
    titleMargin
    0.53
    DMETHOD
    0.52
     мәкалә
    0.51
    archiviato
    0.50
    יתוף
    0.50
    <bos>
    0.50
    Activations Density 0.947%

    No Known Activations