© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4244
    Prev
    Next
    INDEX
    Explanations

    references to committees or groups of people involved in decision-making or organizational contexts

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

    groups or committees of people with specific roles or affiliations.

    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
    Tür
    -0.42
     ब्रेकडाउन
    -0.40
     كومونز
    -0.40
     tartalomajánló
    -0.40
    /***/
    -0.36
    awtextra
    -0.35
     Neder
    -0.35
    ://
    -0.34
    Externé
    -0.34
    slv
    -0.34
    POSITIVE LOGITS
     consisting
    1.08
     comprised
    1.05
     composed
    1.01
     members
    0.98
     consists
    0.91
     composta
    0.91
     consisted
    0.89
     består
    0.89
     composée
    0.86
     comprising
    0.86
    Activations Density 0.688%

    No Known Activations