© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12568
    Prev
    Next
    INDEX
    Explanations

    function calls and structure definitions in a programming context

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

    Code related to GTK tree views

    np_acts-logits-general · gemini-2.0-flash

    ocytes insensitive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    UrlResolution
    -0.63
     localVar
    -0.61
     surla
    -0.54
    ंदीखरीदारी
    -0.53
     ब्रेकडाउन
    -0.53
    SharedCtor
    -0.50
    AddHtmlAttribute
    -0.50
    jspb
    -0.50
    TemporalType
    -0.50
    quiao
    -0.49
    POSITIVE LOGITS
     atoms
    0.51
     Hildebrand
    0.50
    Client
    0.49
    الحياه
    0.49
    ronesia
    0.48
    Buildable
    0.48
    ⓧ
    0.48
    Identyfik
    0.48
     signal
    0.48
     client
    0.48
    Activations Density 0.411%

    No Known Activations