© 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. 5894
    Prev
    Next
    INDEX
    Explanations

    references to political parties and related activities

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

    first-person singular pronouns and personal narrative voice.

    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
     být
    -0.46
    Personensuche
    -0.45
     líqu
    -0.39
     vouloir
    -0.38
    époque
    -0.38
     válvula
    -0.37
     estándares
    -0.37
     pouvant
    -0.37
     mít
    -0.35
     côtes
    -0.35
    POSITIVE LOGITS
     took
    1.80
     gave
    1.71
     did
    1.69
     went
    1.68
     was
    1.63
     came
    1.48
     became
    1.38
     drew
    1.36
     didn
    1.35
     drove
    1.31
    Activations Density 4.915%

    No Known Activations