© 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. 40-GEMMASCOPE-RES-16K
    11. 1555
    Prev
    Next
    INDEX
    Explanations

    nouns related to magical or fantastical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chieht
    -0.55
     ChromeDriver
    -0.36
    хьтан
    -0.36
    atteindre
    -0.35
     deportivo
    -0.35
    VersionUID
    -0.35
    chenkt
    -0.34
     alguno
    -0.34
     vectorielle
    -0.34
    extrémité
    -0.34
    POSITIVE LOGITS
    cape
    1.04
    cript
    1.03
    chool
    1.02
    heet
    1.02
    pace
    1.02
    hift
    1.01
    hip
    0.96
    hape
    0.96
    peed
    0.96
    creen
    0.96
    Activations Density 1.813%

    No Known Activations