Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53458
    Prev
    Next
    INDEX
    Explanations

    file paths and component declarations in code

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

    component templates or code files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.51
    writeFieldEnd
    -0.50
     humo
    -0.47
     atenção
    -0.44
    LLocation
    -0.44
     ankaŭ
    -0.43
    invokeLater
    -0.43
    piew
    -0.42
    TTY
    -0.42
     arreg
    -0.41
    POSITIVE LOGITS
    IBOutlet
    0.72
    .*")]
    0.72
     AssemblyTitle
    0.68
    SpringBootTest
    0.68
    memberof
    0.65
     ReactDOM
    0.65
     './
    0.64
    InjectAttribute
    0.63
     مشين
    0.63
     "..\..\
    0.63
    Activations Density 0.005%

    No Known Activations