© 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. 1-GEMMASCOPE-RES-16K
    6. 8869
    Prev
    Next
    INDEX
    Explanations

    mentions of tasks or task-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.55
    الإنجليزية
    -0.47
    URLException
    -0.46
    ("'"
    -0.45
     kasarigan
    -0.44
     Económica
    -0.44
    "]();
    -0.43
     defects
    -0.43
     fotográfica
    -0.43
    %"),
    -0.42
    POSITIVE LOGITS
     Task
    0.58
    jsonwebtoken
    0.58
     contract
    0.57
     County
    0.55
    findAll
    0.52
    contract
    0.52
     Seminary
    0.50
    Task
    0.48
     Defense
    0.48
    endif
    0.47
    Activations Density 0.207%

    No Known Activations