© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7043
    Prev
    Next
    INDEX
    Explanations

    entities and names related to characters in a narrative

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

    First-person narration

    np_acts-logits-general · gemini-2.0-flash

    subject's actions or thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.74
    NameInMap
    -0.72
     AssemblyTitle
    -0.71
    BoxShadow
    -0.64
    addCriterion
    -0.62
    PhysRevLett
    -0.62
     @"/
    -0.61
     actionMode
    -0.60
     PyTuple
    -0.59
    principalTable
    -0.57
    POSITIVE LOGITS
     knew
    0.81
     thought
    0.79
     hadn
    0.78
     felt
    0.67
     know
    0.66
     remember
    0.65
     hope
    0.64
    心想
    0.64
     wondered
    0.63
     think
    0.62
    Activations Density 0.321%

    No Known Activations