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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8364
    Prev
    Next
    INDEX
    Explanations

    references to types of forms or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.52
     Strecke
    -0.49
    MigrationBuilder
    -0.46
     Sünde
    -0.45
     Betreuung
    -0.44
     Neves
    -0.44
    #
    -0.43
    MockBean
    -0.41
     Menschheit
    -0.40
     Ruhe
    -0.40
    POSITIVE LOGITS
     form
    3.53
     Form
    3.39
    form
    3.22
    Form
    3.20
     FORM
    3.06
    FORM
    2.72
     forms
    2.70
     Forms
    2.61
    forms
    2.47
    Forms
    2.44
    Activations Density 0.219%

    No Known Activations