© 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. 28-GEMMASCOPE-RES-16K
    6. 7732
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and packages related to document formatting and typography

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

    LaTeX package names or code snippets

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.65
    SourceChecksum
    -0.65
    $_['
    -0.65
    ngrx
    -0.60
     مرئيه
    -0.59
    ViewChild
    -0.58
    !”.
    -0.55
     ویکی‌پدی
    -0.55
    HasColumnType
    -0.55
     Meksiku
    -0.55
    POSITIVE LOGITS
     kultury
    0.41
     quelquefois
    0.40
     juridiques
    0.40
     internationaux
    0.40
     culturelle
    0.37
     pédagogique
    0.37
     culturelles
    0.37
     informée
    0.35
     nød
    0.35
     souri
    0.35
    Activations Density 0.122%

    No Known Activations