© 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. 39-GEMMASCOPE-RES-16K
    6. 4097
    Prev
    Next
    INDEX
    Explanations

    structural elements and properties in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\
    -0.42
    ViewFeatures
    -0.39
    '\\
    -0.37
    -\\
    -0.36
    $.\\
    -0.35
    ondissement
    -0.34
    ?\\
    -0.34
     \\
    -0.34
    }$.\\
    -0.34
    发表于
    -0.32
    POSITIVE LOGITS
     Audiodateien
    0.60
     defaultstate
    0.55
     désolés
    0.55
    IBOutlet
    0.55
     surla
    0.53
    numerusform
    0.51
     utafitiHapana
    0.50
    𞤑
    0.50
     externi
    0.50
    DispatchToProps
    0.49
    Activations Density 0.181%

    No Known Activations