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. 23-GEMMASCOPE-RES-16K
    6. 5901
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical data or patterns within structured contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    squareup
    -0.52
    Więcej
    -0.49
    Getenv
    -0.49
    iformis
    -0.49
    Còn
    -0.48
    engono
    -0.47
     Wert
    -0.47
    </tfoot>
    -0.47
    LLES
    -0.46
     pull
    -0.45
    POSITIVE LOGITS
    Ta
    0.75
     TestBed
    0.63
    RTSC
    0.62
    RegressionTest
    0.60
    :✨
    0.59
    новниш
    0.58
     Duits
    0.57
    AutoScaleMode
    0.56
    +)
    0.55
     Comédie
    0.55
    Activations Density 0.241%

    No Known Activations