© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6650
    Prev
    Next
    INDEX
    Explanations

    instances of programmatic functions and variables in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -1.02
    ourites
    -0.79
    tawesome
    -0.76
    OfBirth
    -0.75
    ceutical
    -0.73
    webtoken
    -0.71
    lapping
    -0.67
    AxisSize
    -0.66
    giène
    -0.65
    firmasi
    -0.65
    POSITIVE LOGITS
    aimana
    0.71
    etheless
    0.61
    unteers
    0.49
    awaiter
    0.45
    sterious
    0.43
    utenant
    0.43
    ccoli
    0.42
    esian
    0.41
    aporation
    0.40
    iterranean
    0.40
    Activations Density 1.100%

    No Known Activations