© 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. 4342
    Prev
    Next
    INDEX
    Explanations

    references to press briefings and interviews involving public figures

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

    pronouns and verbs associated with people speaking or being quoted in news articles.

    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
     write
    -0.44
     Write
    -0.43
     vacío
    -0.38
     WRITE
    -0.37
    Condu
    -0.37
     presentaciones
    -0.36
     writes
    -0.36
    $_['
    -0.35
     blog
    -0.35
    
    -0.35
    POSITIVE LOGITS
     references
    0.65
     reminis
    0.64
     referencing
    0.64
     reference
    0.60
     reiter
    0.60
     referring
    0.59
     candid
    0.57
     expressing
    0.56
     acknowledging
    0.55
     espri
    0.55
    Activations Density 0.416%

    No Known Activations