© 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. 8-GEMMASCOPE-RES-16K
    6. 6569
    Prev
    Next
    INDEX
    Explanations

    elements related to panels or panel discussions in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.48
     devait
    -0.35
    ...”
    -0.35
    useNewUrlParser
    -0.35
     haremos
    -0.35
    }}}{
    -0.34
    :“
    -0.33
     sûr
    -0.32
    ”“
    -0.32
     électrique
    -0.31
    POSITIVE LOGITS
     panel
    3.06
     Panel
    2.95
    Panel
    2.73
     panels
    2.69
    panel
    2.69
     PANEL
    2.63
     Panels
    2.63
    PANEL
    2.31
    Panels
    2.30
    panels
    2.25
    Activations Density 0.104%

    No Known Activations