© 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. 10-GEMMASCOPE-RES-16K
    6. 6352
    Prev
    Next
    INDEX
    Explanations

    references to libraries and configurations in programming environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isContained
    -0.79
    GEBURTSDATUM
    -0.71
    SharedCtor
    -0.70
     queſta
    -0.69
    principalColumn
    -0.69
    itinéraire
    -0.66
     AssemblyCompany
    -0.65
     メンテナ
    -0.65
    richTextPanel
    -0.64
    dataclass
    -0.64
    POSITIVE LOGITS
    glGen
    0.56
    GLenum
    0.49
    glDelete
    0.44
    gl
    0.38
     gl
    0.36
     GL
    0.34
     Gl
    0.33
     en
    0.32
    GL
    0.29
     Cap
    0.28
    Activations Density 0.862%

    No Known Activations