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. 12175
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and inquiries regarding outcomes or expectations

    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
     mxArray
    -0.65
     unknownFields
    -0.61
    buie
    -0.58
    glBegin
    -0.55
    fortawesome
    -0.51
    OrWhiteSpace
    -0.50
    存于互联网档案馆
    -0.50
     كومونز
    -0.49
    بران
    -0.48
    égard
    -0.48
    POSITIVE LOGITS
     so
    4.11
    so
    2.91
    So
    2.66
     So
    2.63
     så
    2.21
     SO
    2.04
     так
    1.93
    所以
    1.93
     così
    1.92
     sooo
    1.72
    Activations Density 1.380%

    No Known Activations