© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 64900
    Prev
    Next
    INDEX
    Explanations

    elements related to coding syntax, specifically identifiers and variables in programming languages

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

    variable names and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    隠れ
    -0.41
     صوتيه
    -0.40
    Билгалдахарш
    -0.37
     المعيارى
    -0.37
     floresta
    -0.36
    stylers
    -0.35
    InstrumentedTest
    -0.35
     CanadaChoose
    -0.35
     redonda
    -0.34
    Ly
    -0.32
    POSITIVE LOGITS
     UITextField
    0.65
     myſelf
    0.58
     variables
    0.55
     Variable
    0.54
    syms
    0.54
     SimpleName
    0.54
     variabel
    0.54
    ſelf
    0.54
     Variables
    0.52
     itſelf
    0.52
    Activations Density 1.309%

    No Known Activations