© 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. 21-GEMMASCOPE-RES-16K
    11. 15770
    Prev
    Next
    INDEX
    Explanations

    closing braces and semicolons in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.71
    SharedDtor
    -0.71
    AutoScale
    -0.69
    LookAnd
    -0.63
    ISupport
    -0.61
    localctx
    -0.60
    脚注の使い方
    -0.60
    Diweddarwch
    -0.60
    PyExc
    -0.59
    tvguidetime
    -0.57
    POSITIVE LOGITS
     esf
    0.41
     épis
    0.36
     AssemblyTitle
    0.35
    ſelves
    0.34
     obligado
    0.34
     Diſ
    0.32
     Sp
    0.31
     foncé
    0.31
    änderung
    0.31
    AsUp
    0.31
    Activations Density 0.122%

    No Known Activations