© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13735
    Prev
    Next
    INDEX
    Explanations

    occurrences of first-person references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences starting with "As [pronoun]"

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.64
     even
    -0.58
     persino
    -0.58
     addirittura
    -0.57
     jopa
    -0.56
     بيها
    -0.56
     bahkan
    -0.55
     enough
    -0.54
     actually
    -0.53
     Enough
    -0.53
    POSITIVE LOGITS
     prepares
    1.05
     prepare
    0.96
     nears
    0.95
     Paglinawan
    0.88
     await
    0.87
     awaited
    0.85
     awaits
    0.84
     progresses
    0.80
     prepared
    0.79
     preparation
    0.78
    Activations Density 0.183%

    No Known Activations