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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 15768
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and evaluations of materials or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.82
     estekak
    -0.79
     propOrder
    -0.79
    DockStyle
    -0.76
    expandindo
    -0.73
    rungsseite
    -0.73
    SequentialGroup
    -0.69
    Obrázky
    -0.62
     INTERESAR
    -0.62
    Biographie
    -0.61
    POSITIVE LOGITS
     financially
    1.53
     musically
    1.45
     physically
    1.31
     spiritually
    1.27
     Physically
    1.22
     economically
    1.21
     psychologically
    1.21
     intellectually
    1.20
     academically
    1.18
     visually
    1.16
    Activations Density 1.117%

    No Known Activations