© 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. 14068
    Prev
    Next
    INDEX
    Explanations

    employment-related concepts and their implications in discussions

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

    citation and attribution patterns, particularly phrases that introduce sources, evidence, or expert opinions.

    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
    хьтан
    -0.77
     myſelf
    -0.71
    aarrggbb
    -0.70
     itſelf
    -0.69
     queſta
    -0.68
    OGND
    -0.67
     Italijanski
    -0.67
     ſche
    -0.66
     purpoſe
    -0.65
    <unused43>
    -0.64
    POSITIVE LOGITS
     there
    0.97
    there
    0.58
    There
    0.50
     THERE
    0.49
     There
    0.46
    THERE
    0.46
     humans
    0.43
     people
    0.42
     theres
    0.41
     everything
    0.40
    Activations Density 1.329%

    No Known Activations