© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8250
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that code or content has been automatically generated

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

    Code generation/auto-generation related tokens

    np_acts-logits-general · gemini-2.0-flash

    generated by code

    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
    addCriterion
    -0.70
    AndEndTag
    -0.67
     disambiguazione
    -0.67
    SourceChecksum
    -0.65
    LookAnd
    -0.65
    verwijspagina
    -0.63
    IntoConstraints
    -0.62
    protoimpl
    -0.61
    SharedDtor
    -0.60
     wireType
    -0.60
    POSITIVE LOGITS
    CodeAttribute
    2.63
    CodeDom
    0.75
    GeneratedCode
    0.64
     nakalista
    0.47
    codegen
    0.41
     attribute
    0.40
    gcc
    0.40
    getAttribute
    0.40
    setAttribute
    0.40
     Edge
    0.38
    Activations Density 0.011%

    No Known Activations