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. 6447
    Prev
    Next
    INDEX
    Explanations

    instances of the word "see" and its variations, indicating a focus on perception and observation

    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
     bezeichneter
    -0.76
     contextLoads
    -0.73
    bitat
    -0.61
     XNUMX
    -0.60
     raiſ
    -0.58
    ungkinan
    -0.58
     quelcon
    -0.58
    mahaman
    -0.57
     faptul
    -0.57
     peines
    -0.56
    POSITIVE LOGITS
     how
    0.91
     clearly
    0.91
     firsthand
    0.88
     fit
    0.81
     وتسجيلات
    0.81
     glimpses
    0.81
    Saw
    0.75
    emed
    0.74
     sees
    0.74
     eye
    0.72
    Activations Density 0.157%

    No Known Activations