Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9185
    Prev
    Next
    INDEX
    Explanations

    references to live music events and the associated performers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    queryInterface
    -0.58
     Nunn
    -0.57
     pengar
    -0.56
    Lycka
    -0.56
    fhir
    -0.52
    timestamps
    -0.52
     reference
    -0.52
    MigrationBuilder
    -0.51
     dimensi
    -0.51
     dimen
    -0.50
    POSITIVE LOGITS
    IndentedString
    0.62
     guest
    0.59
     lineup
    0.57
     featured
    0.56
     artists
    0.55
     artist
    0.53
    SourceChecksum
    0.52
     invited
    0.52
    Guest
    0.50
     feature
    0.50
    Activations Density 0.173%

    No Known Activations