© 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. 31-GEMMASCOPE-RES-16K
    11. 8984
    Prev
    Next
    INDEX
    Explanations

    patterns or symbols related to code structures and definitions

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

    C/C++ compiler type annotations and endianness declarations (like `__be32`, `__u8`, `__LITTLE_ENDIAN_BITFIELD`).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.59
     للمعارف
    -0.54
    TestingModule
    -0.51
    Datuak
    -0.48
    verwijspagina
    -0.47
    MessageWindow
    -0.46
    lankton
    -0.46
    IVEREF
    -0.45
    CascadeType
    -0.45
    HideFlags
    -0.45
    POSITIVE LOGITS
     __
    0.68
     '__
    0.61
    /__
    0.61
     "__
    0.59
    #__
    0.59
    ("__
    0.59
    .__
    0.57
    ().__
    0.57
    ->__
    0.57
    (__
    0.55
    Activations Density 0.170%

    No Known Activations