© 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. 4839
    Prev
    Next
    INDEX
    Explanations

    official announcements related to companies or entities

    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
    AsUp
    -0.52
     ritratto
    -0.47
     prossimo
    -0.46
     caneca
    -0.44
     tramonto
    -0.43
    ⓧ
    -0.42
     attualmente
    -0.42
     sapore
    -0.41
     antigüedad
    -0.40
     almohada
    -0.40
    POSITIVE LOGITS
    GEBURTS
    0.49
    yarnpkg
    0.47
    enderror
    0.47
    EndInit
    0.45
    OrBuilder
    0.45
     مرئيه
    0.44
    VIA
    0.44
    signs
    0.43
     "];
    0.43
     undec
    0.42
    Activations Density 1.635%

    No Known Activations