© 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. 2501
    Prev
    Next
    INDEX
    Explanations

    terms related to reaction and response

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

    Following forms of "respond" or "react"

    np_acts-logits-general · gemini-2.0-flash

    responding to stimuli

    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
     otomatig
    -0.89
    ///</
    -0.79
    withIdentifier
    -0.76
    IntoConstraints
    -0.74
     ویکی‌پدی
    -0.71
    bootstrapcdn
    -0.69
     transfieras
    -0.69
    BufferException
    -0.68
     OFDb
    -0.67
     nakalista
    -0.65
    POSITIVE LOGITS
     heavily
    0.65
     favorably
    0.63
     greatly
    0.61
     extensively
    0.61
     migh
    0.61
     positively
    0.60
     favourably
    0.60
     strongly
    0.60
     differently
    0.58
     accordingly
    0.57
    Activations Density 0.387%

    No Known Activations