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
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8526
    Prev
    Next
    INDEX
    Explanations

    terms related to subjects in motion or photography contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     불
    -0.32
     Grundstück
    -0.30
     Comissão
    -0.30
     tug
    -0.30
     not
    -0.28
     army
    -0.27
     land
    -0.27
    论
    -0.27
     Aguilar
    -0.26
     article
    -0.25
    POSITIVE LOGITS
    isContained
    0.78
    MLLoader
    0.75
     JpaRepository
    0.64
     مشين
    0.64
    oredCriteria
    0.63
    AccessorTable
    0.62
    StructEnd
    0.61
    
    0.61
    IsMutable
    0.60
    jsxFileName
    0.59
    Activations Density 0.314%

    No Known Activations