© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 524
    Prev
    Next
    INDEX
    Explanations

    terms related to administrative or legal processes

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

    technical or specialized terms related to specific domains (like medical terms, scientific terminology, professional jargon).

    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
    esthes
    -0.63
     ngân
    -0.61
     فريبيس
    -0.61
    tanleria
    -0.60
     '\\;'
    -0.59
     Inscrivez
    -0.54
    XmlAccessType
    -0.53
    PreInfinity
    -0.53
    ungeons
    -0.52
    óngase
    -0.52
    POSITIVE LOGITS
    LikeLike
    0.48
     번째
    0.47
     createState
    0.45
     dual
    0.44
     extra
    0.43
     tame
    0.42
     elite
    0.42
     protest
    0.40
     test
    0.40
    的な
    0.40
    Activations Density 0.668%

    No Known Activations