© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3236
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional intelligence and interpersonal relationships

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

    words and phrases related to causing harm, damage, or negative consequences to others.

    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
    DoubleQuotes
    -0.38
    endpush
    -0.37
    RTLU
    -0.35
    Referanser
    -0.32
    GraphicsUnit
    -0.32
    ﾟ)
    -0.32
    InputTagHelper
    -0.32
    ]")]
    -0.32
    Xna
    -0.31
    modb
    -0.31
    POSITIVE LOGITS
     others
    2.80
    others
    2.50
    Others
    2.50
     Others
    2.47
     OTHERS
    2.31
     دیگران
    2.00
    别人
    1.85
    別人
    1.77
    别人的
    1.70
    他人
    1.66
    Activations Density 0.758%

    No Known Activations