© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 11643
    Prev
    Next
    INDEX
    Explanations

    terms related to media coverage and public access to information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    género
    -0.47
    equalTo
    -0.44
     táctil
    -0.43
    sträger
    -0.42
     beszél
    -0.41
    berian
    -0.41
     vzh
    -0.40
     ngào
    -0.40
    ::<
    -0.40
    GARET
    -0.39
    POSITIVE LOGITS
     spectators
    0.93
     watching
    0.92
     متعلقه
    0.90
     spectator
    0.86
     Watching
    0.86
    Watching
    0.83
    watching
    0.79
     observer
    0.79
     Attend
    0.79
    DoubleQuotes
    0.78
    Activations Density 0.198%

    No Known Activations