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. 12001
    Prev
    Next
    INDEX
    Explanations

    terms related to contributions and acknowledgments in research papers

    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
    ,»
    -1.12
    «.
    -1.02
    «,
    -0.88
    .»
    -0.87
    rawDesc
    -0.86
    !»
    -0.86
    !».
    -0.86
    ,«
    -0.84
    «
    -0.83
    ?»
    -0.81
    POSITIVE LOGITS
    ________________
    1.71
    ................
    1.69
    ----------------
    1.61
     ________
    1.59
    ****************
    1.58
    ____________
    1.50
     ____________
    1.47
    _______________
    1.47
     ___________
    1.45
    ___________
    1.45
    Activations Density 1.118%

    No Known Activations