© 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. 15-GEMMASCOPE-RES-16K
    11. 1627
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and function names

    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
     ब्रेकडाउन
    -0.58
    astify
    -0.56
     препратки
    -0.54
    parsedMessage
    -0.54
    Geplaatst
    -0.52
    FunctionFlags
    -0.49
     onCreateView
    -0.48
     '\\;'
    -0.48
    AsUp
    -0.47
    awtextra
    -0.47
    POSITIVE LOGITS
    tagPool
    0.44
     Lauf
    0.41
     available
    0.40
    ecore
    0.40
     Schwarz
    0.40
     Figue
    0.40
    ophyta
    0.39
    IFER
    0.39
    zim
    0.39
     Lob
    0.39
    Activations Density 0.147%

    No Known Activations