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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10774
    Prev
    Next
    INDEX
    Explanations

    evaluations of performances in artistic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attributed statements, claims, and factual assertions made by identified individuals or sources.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $_"
    -0.73
    DockStyle
    -0.66
    expandindo
    -0.66
    цезда
    -0.64
    bootstrapcdn
    -0.63
    IntoConstraints
    -0.60
    ロウィン
    -0.60
    twimg
    -0.58
    rungsseite
    -0.58
    Vidite
    -0.58
    POSITIVE LOGITS
     "
    3.06
     “
    2.70
     „
    2.05
     «
    1.92
    「
    1.91
     "...
    1.86
     ``
    1.83
     "[
    1.81
     "'
    1.75
     ''
    1.73
    Activations Density 6.123%

    No Known Activations