© 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. 24-GEMMASCOPE-RES-16K
    11. 5864
    Prev
    Next
    INDEX
    Explanations

    phrases introducing people and their roles or attributes

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

    Clauses starting with "who" or "which"

    np_acts-logits-general · gemini-2.0-flash

    who or which followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    かな
    -0.36
    ang
    -0.34
     gibi
    -0.34
     these
    -0.34
     phải
    -0.33
     sure
    -0.33
     anyone
    -0.32
     interes
    -0.31
     points
    -0.31
     ve
    -0.31
    POSITIVE LOGITS
    ScopeManager
    0.83
    CppMethod
    0.71
    principalTable
    0.68
    脚注の使い方
    0.67
    findpost
    0.66
    ArrowToggle
    0.66
    TagMode
    0.66
    帖最后由
    0.66
    ChildScrollView
    0.66
     estekak
    0.65
    Activations Density 0.166%

    No Known Activations