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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14874
    Prev
    Next
    INDEX
    Explanations

    numerical values and metrics, particularly related to data or measurements

    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
     فريبيس
    -0.72
    ionales
    -0.65
    Autoritní
    -0.63
    ussis
    -0.59
     Pingback
    -0.57
    ührung
    -0.56
     Etr
    -0.56
    はじめに
    -0.55
     Raceway
    -0.55
    GOTREF
    -0.54
    POSITIVE LOGITS
    
    0.76
    sprung
    0.50
     WaitForSeconds
    0.49
    useNewUrlParser
    0.49
    thus
    0.48
    .
    0.48
    dot
    0.48
    posedge
    0.46
     Thus
    0.45
     glyphicon
    0.45
    Activations Density 0.400%

    No Known Activations