© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1470
    Prev
    Next
    INDEX
    Explanations

    code-related terminology, specifically related to function and variable definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.50
    WithIOException
    -0.47
    uxxxx
    -0.45
     kasarigan
    -0.45
    انتهای
    -0.43
    ohist
    -0.42
    ftagPool
    -0.42
    Besos
    -0.41
     crossorigin
    -0.39
     препратки
    -0.39
    POSITIVE LOGITS
    CodeAttribute
    0.55
     Taktlose
    0.47
    তথ্যসূত্র
    0.44
    OGND
    0.42
     WPS
    0.41
     Parlement
    0.41
     חיצוניים
    0.41
    BibitemShut
    0.40
    Insee
    0.40
     MPS
    0.39
    Activations Density 0.280%

    No Known Activations