© 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. 38-GEMMASCOPE-RES-16K
    6. 15781
    Prev
    Next
    INDEX
    Explanations

    elements related to various forms of storytelling and narrative in films and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GRAPHY
    -0.36
    verhält
    -0.36
    keits
    -0.34
    ünstig
    -0.34
    drücke
    -0.32
    ISTRATION
    -0.31
    haltens
    -0.30
    gemeins
    -0.30
    fertigung
    -0.29
    tigkeits
    -0.29
    POSITIVE LOGITS
    work
    0.76
    point
    0.76
    marks
    0.76
    guard
    0.75
    fellow
    0.74
    mark
    0.73
    bread
    0.73
    court
    0.73
    bill
    0.73
    leaf
    0.72
    Activations Density 1.565%

    No Known Activations