Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6135
    Prev
    Next
    INDEX
    Explanations

    references to political dynamics and personal relationships within a political context

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

    intent to join

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     enfans
    -0.36
     posiad
    -0.28
    WebElementEntity
    -0.27
     contiennent
    -0.27
     eingerichtet
    -0.27
     šal
    -0.26
    ויות
    -0.26
    radura
    -0.25
     nærm
    -0.25
    กัน
    -0.25
    POSITIVE LOGITS
     joining
    2.06
     Joining
    1.92
     join
    1.88
    Joining
    1.88
    joining
    1.72
     joins
    1.70
     Join
    1.69
     joined
    1.68
    join
    1.66
     JOIN
    1.63
    Activations Density 0.196%

    No Known Activations