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. 9-GEMMASCOPE-RES-131K
    6. 119603
    Prev
    Next
    INDEX
    Explanations

    references to parties involved in agreements or negotiations

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

    parties' actions and agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teacher
    -0.36
     car
    -0.34
     girl
    -0.33
     emission
    -0.30
    不过
    -0.29
     fit
    -0.29
     ویکی‌پدی
    -0.28
     mel
    -0.28
    "}")
    -0.28
    isNameExpr
    -0.27
    POSITIVE LOGITS
     parties
    0.82
    parties
    0.75
     Parties
    0.73
     calendriers
    0.69
     esternos
    0.65
    Parties
    0.64
     PARTIES
    0.63
     Parteien
    0.60
    InitVars
    0.59
     stakeholders
    0.58
    Activations Density 0.120%

    No Known Activations