© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1425
    Prev
    Next
    INDEX
    Explanations

    instances of positivity and good feelings in various contexts

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

    Mentions "positive" or "positively"

    np_acts-logits-general · gemini-2.0-flash

    positive events and outcomes

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Trung
    -0.33
     Brenn
    -0.33
     Berman
    -0.31
     Deutschlands
    -0.30
    icona
    -0.30
     ressemble
    -0.30
     blasphemy
    -0.30
    rasi
    -0.30
     built
    -0.30
     striking
    -0.30
    POSITIVE LOGITS
    Positive
    0.82
     positive
    0.78
     Positive
    0.78
    positive
    0.77
     positif
    0.76
     positivas
    0.75
     POSITIVE
    0.72
     positivity
    0.72
     positiva
    0.70
     positivo
    0.68
    Activations Density 0.537%

    No Known Activations