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. 12466
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, particularly operators and structure delimiters

    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
    ^(@)
    -1.54
     $_"
    -1.43
    NUMX
    -1.42
    >\<^
    -1.39
    tvguidetime
    -1.34
    intenance
    -1.33
    ^(@
    -1.30
     Efq
    -1.30
    leſs
    -1.26
     للمعارف
    -1.25
    POSITIVE LOGITS
      
    1.22
    to
    0.97
       
    0.95
    this
    0.94
    is
    0.93
    for
    0.92
    has
    0.91
    i
    0.90
    a
    0.89
    in
    0.88
    Activations Density 1.252%

    No Known Activations