© 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. 31-GEMMASCOPE-RES-16K
    6. 1887
    Prev
    Next
    INDEX
    Explanations

    instructions and warnings related to medical guidelines and safety precautions

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

    warnings and instructions about medication usage.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    instructional text with cautionary warnings and safety guidelines.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.94
    bootstrapcdn
    -0.68
     nahilalakip
    -0.67
    MLLoader
    -0.62
     дописавши
    -0.61
    IUrlHelper
    -0.61
     createSlice
    -0.59
    DockStyle
    -0.57
    +:+
    -0.56
    abestanden
    -0.56
    POSITIVE LOGITS
     always
    1.24
     Always
    1.22
    Always
    1.20
     Avoid
    1.16
     avoid
    1.16
    Avoid
    1.13
     ALWAYS
    1.05
    always
    1.04
     NEVER
    0.98
    avoid
    0.98
    Activations Density 0.296%

    No Known Activations