© 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. 0-GEMMASCOPE-RES-16K
    6. 2575
    Prev
    Next
    INDEX
    Explanations

    instances of agreement or consensus between parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.70
     wikipagina
    -0.69
     anún
    -0.59
    ptonshire
    -0.57
     femininas
    -0.57
     engraçadas
    -0.54
     समीक्षक
    -0.54
    hassee
    -0.54
     Bewußt
    -0.53
     tramonto
    -0.53
    POSITIVE LOGITS
     Tunnel
    0.65
     tunnel
    0.62
    Tunnel
    0.57
    ids
    0.56
     United
    0.56
    BACKGROUND
    0.55
    Background
    0.54
    United
    0.52
     District
    0.52
     Agreement
    0.51
    Activations Density 0.423%

    No Known Activations