© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4726
    Prev
    Next
    INDEX
    Explanations

    information about film productions and productions related to specific stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ❮
    -0.35
    holders
    -0.35
    ungsbedingungen
    -0.34
    efois
    -0.33
    awtextra
    -0.33
    Datuak
    -0.33
    suchen
    -0.33
    cuits
    -0.32
    zustellen
    -0.32
    uldron
    -0.32
    POSITIVE LOGITS
     starring
    1.20
    Starring
    0.93
     Starring
    0.92
     protagon
    0.91
     featuring
    0.91
     starred
    0.82
     depicts
    0.81
    featuring
    0.79
     premiered
    0.79
     loosely
    0.77
    Activations Density 0.334%

    No Known Activations