© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12853
    Prev
    Next
    INDEX
    Explanations

    references to technical or computational tasks

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

    timestamps and user tags

    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
    Dimensões
    -0.32
     např
    -0.31
     namorado
    -0.30
    verwijspagina
    -0.30
     informée
    -0.29
     ČR
    -0.29
     bờ
    -0.28
     senderos
    -0.27
     cuota
    -0.27
    yaç
    -0.26
    POSITIVE LOGITS
    SOUNDBITE
    0.68
    interopRequire
    0.66
    InitVars
    0.63
     nahilalakip
    0.59
    InputTagHelper
    0.57
    WithIOException
    0.55
     виправивши
    0.54
     StatefulWidget
    0.53
     defaultstate
    0.53
    cticut
    0.51
    Activations Density 0.705%

    No Known Activations