© 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. 11-GEMMASCOPE-RES-16K
    6. 4804
    Prev
    Next
    INDEX
    Explanations

    technical symbols and units related to scientific measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     collage
    -0.54
     IAP
    -0.54
     cola
    -0.49
     potes
    -0.49
    pep
    -0.49
    gridy
    -0.49
     tira
    -0.48
     chat
    -0.47
     Quota
    -0.47
     pep
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.71
    extré
    0.55
     agresión
    0.54
    ientôt
    0.54
    ResponseWriter
    0.54
     ajudá
    0.53
     ibunya
    0.53
     Autorisations
    0.52
     istrinya
    0.52
     liitty
    0.51
    Activations Density 0.500%

    No Known Activations