© 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. 1594
    Prev
    Next
    INDEX
    Explanations

    instances of error handling and model management in programming contexts

    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
    InitVars
    -0.45
     فريبيس
    -0.44
     nakalista
    -0.44
    MessageOf
    -0.37
     hikariConfig
    -0.35
    bitos
    -0.35
     accessoires
    -0.35
    Mixtures
    -0.34
    دانشنامهٔ
    -0.33
    JOptionPane
    -0.32
    POSITIVE LOGITS
     ujednoznacz
    0.53
    RTEE
    0.52
    ValueStyle
    0.48
    parsedMessage
    0.45
     beginnetje
    0.44
    хівовано
    0.44
    ResumeLayout
    0.44
    prepareStatement
    0.42
    SPATH
    0.42
    UnusedPrivate
    0.41
    Activations Density 0.400%

    No Known Activations