© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    references to regulations and procedures within a correctional facility

    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
    aminya
    -0.41
    bootstrapcdn
    -0.37
     markt
    -0.37
     vetorial
    -0.35
    chengladbach
    -0.35
     vectorielle
    -0.35
     énergé
    -0.34
     vektor
    -0.34
    NoStop
    -0.34
    redient
    -0.33
    POSITIVE LOGITS
     prison
    1.86
     prisoners
    1.72
     inmates
    1.70
     inmate
    1.67
    prison
    1.67
     Prison
    1.67
    Prison
    1.67
     prisoner
    1.63
     prisons
    1.59
     Prisoners
    1.48
    Activations Density 1.597%

    No Known Activations