Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8195
    Prev
    Next
    INDEX
    Explanations

    URL patterns and query parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.59
    出版年
    -0.57
    verwijspagina
    -0.56
     ſche
    -0.48
    Hozzáférés
    -0.46
     queſta
    -0.46
     ſur
    -0.46
    apunov
    -0.45
     houſe
    -0.45
     cæ
    -0.43
    POSITIVE LOGITS
    hl
    0.46
    rel
    0.43
    sa
    0.38
    fe
    0.38
    HostException
    0.38
    getClassLoader
    0.38
    feature
    0.36
    sk
    0.36
    nom
    0.36
    gl
    0.36
    Activations Density 0.343%

    No Known Activations