© 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. 2057
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to software architecture and API structures

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

    technical URL or code-related tokens and paths.

    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
    rungsseite
    -0.75
    webElement
    -0.70
    principalColumn
    -0.63
     препратки
    -0.61
     fubject
    -0.60
     zoude
    -0.60
     وتسجيلات
    -0.58
    KommentareTeilen
    -0.57
    +#+#
    -0.57
    ValueStyle
    -0.57
    POSITIVE LOGITS
     HQ
    0.35
    sobí
    0.31
    culable
    0.31
    geb
    0.31
    gericht
    0.31
    SC
    0.30
    ēr
    0.30
    maßen
    0.29
     nép
    0.29
    global
    0.29
    Activations Density 0.535%

    No Known Activations