© 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. 39-GEMMASCOPE-RES-16K
    11. 3304
    Prev
    Next
    INDEX
    Explanations

    specific alphanumeric identifiers or codes

    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
    nappropriate
    -0.88
    tualmente
    -0.87
    guien
    -0.84
    достатки
    -0.77
    словия
    -0.72
    cestor
    -0.60
    ertia
    -0.59
    dasarkan
    -0.59
    herited
    -0.58
    нимание
    -0.58
    POSITIVE LOGITS
    которые
    1.23
    withstanding
    1.09
    foundland
    0.94
    giveness
    0.90
    ympto
    0.76
    ergies
    0.73
    tonsoft
    0.69
    nadequate
    0.65
    structors
    0.65
    greSQL
    0.65
    Activations Density 1.385%

    No Known Activations