Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7452
    Prev
    Next
    INDEX
    Explanations

    terms related to streaming and data transfer processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    Anhalt
    -0.83
     Apos
    -0.80
    ایج
    -0.78
     Dory
    -0.75
     McDowell
    -0.75
    QUOTES
    -0.74
     Dickinson
    -0.74
    ngdoc
    -0.74
     EH
    -0.73
    GeneratedValue
    -0.73
    POSITIVE LOGITS
     stream
    1.49
     streams
    1.48
     STREAM
    1.43
    stream
    1.42
    streams
    1.42
     Stream
    1.36
     Streams
    1.33
    STREAM
    1.26
    Stream
    1.25
    Streams
    1.11
    Activations Density 0.037%

    No Known Activations