© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6326
    Prev
    Next
    INDEX
    Explanations

    references to families and related social units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -0.48
     ports
    -0.41
     Paglinawan
    -0.39
    ReusableCell
    -0.39
     Edad
    -0.36
     *++
    -0.36
     rêver
    -0.35
    parsedMessage
    -0.35
    caneca
    -0.34
     BoxFit
    -0.34
    POSITIVE LOGITS
     families
    3.05
     Families
    2.78
    Families
    2.72
    families
    2.59
     familles
    2.23
     familias
    2.05
     famiglie
    1.95
     FAMIL
    1.85
     famílias
    1.84
    FAMIL
    1.48
    Activations Density 0.086%

    No Known Activations