© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13720
    Prev
    Next
    INDEX
    Explanations

    programming language constructs such as function definitions, classes, and struct declarations

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

    C/C++ or Javascript code syntax

    np_acts-logits-general · gemini-2.0-flash

    static inline code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     kasarigan
    -1.05
     صوتيه
    -1.04
    StructEnd
    -0.94
     lenker
    -0.92
     autorytatywna
    -0.91
     فريبيس
    -0.88
    OGND
    -0.88
     queſta
    -0.86
    Diweddarwch
    -0.85
    хьтан
    -0.85
    POSITIVE LOGITS
    .
    0.37
     the
    0.37
     
    0.36
    R
    0.35
    The
    0.34
    V
    0.34
     also
    0.34
    M
    0.33
    r
    0.33
    2
    0.33
    Activations Density 0.171%

    No Known Activations