© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12674
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical interactions and integrity of connectors or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.48
     queima
    -0.48
    ihnachten
    -0.41
     zast
    -0.39
    قایناق‌لار
    -0.39
     Radical
    -0.39
    Radical
    -0.39
     Administrativna
    -0.39
    CommonModule
    -0.38
    wäh
    -0.38
    POSITIVE LOGITS
     detach
    1.38
     detachment
    1.30
     detached
    1.28
     loose
    1.15
     separation
    1.09
    detached
    1.08
     loosened
    1.08
     loosen
    1.03
     loosening
    1.03
    Loose
    1.02
    Activations Density 0.562%

    No Known Activations