© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6804
    Prev
    Next
    INDEX
    Explanations

    elements related to reasoning and decision-making processes

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

    text expressing personal opinions, subjective statements, and conversational discourse.

    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
    InjectAttribute
    -0.87
    awtextra
    -0.85
    SharedCtor
    -0.84
     zuſammen
    -0.82
    Autoritní
    -0.81
     يتيمه
    -0.81
    <unused21>
    -0.80
    <unused14>
    -0.79
    <unused8>
    -0.79
    <pad>
    -0.79
    POSITIVE LOGITS
     fucking
    0.36
     bullshit
    0.36
     fucked
    0.36
     stupid
    0.31
     p
    0.31
     crazy
    0.30
     stupidly
    0.30
     okay
    0.29
    nameof
    0.29
     FUCKING
    0.28
    Activations Density 0.194%

    No Known Activations