© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 42293
    Prev
    Next
    INDEX
    Explanations

    terms indicating varying levels of quality or performance

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

    average or moderate

    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
     présidenti
    -0.45
     boat
    -0.44
     Boat
    -0.41
     send
    -0.41
     sticker
    -0.40
    fhir
    -0.39
     join
    -0.39
    AppBar
    -0.39
     Espagne
    -0.39
    Sentence
    -0.38
    POSITIVE LOGITS
     mediocre
    1.69
     mediocrity
    1.53
    medio
    1.20
    Medio
    1.09
     Medio
    1.02
     lukewarm
    0.91
     medio
    0.80
     médio
    0.76
     незавершена
    0.75
     moderately
    0.74
    Activations Density 0.003%

    No Known Activations