© 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. 5196
    Prev
    Next
    INDEX
    Explanations

    syntax elements and keywords related to programming or markup languages

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

    Code, paths, and filenames

    np_acts-logits-general · gemini-2.0-flash

    code snippets and structure

    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
    parsedMessage
    -0.74
    writeFieldEnd
    -0.60
    الدراسه
    -0.57
    MemoryWarning
    -0.55
    HttpPut
    -0.52
     tartalomajánló
    -0.52
     disambiguazione
    -0.51
    complexContent
    -0.51
    PMailer
    -0.51
    AnchorStyles
    -0.50
    POSITIVE LOGITS
     spéciaux
    0.53
     Städ
    0.43
     special
    0.41
    gyi
    0.39
     cortinas
    0.38
    lägen
    0.37
     climatisation
    0.37
     curling
    0.36
     cabine
    0.36
     CROW
    0.35
    Activations Density 0.404%

    No Known Activations