© 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. 7933
    Prev
    Next
    INDEX
    Explanations

    questions or statements about existence or verification

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

    Questions that start with "Is", "Are", or "Does"

    np_acts-logits-general · gemini-2.0-flash

    is does are questions

    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
     AssemblyCulture
    -1.00
    +#+#
    -0.83
     estekak
    -0.81
    tvguidetime
    -0.79
     CreateTagHelper
    -0.75
     Họ
    -0.74
     مرئيه
    -0.73
    IBarButtonItem
    -0.73
    ^(@)
    -0.72
    Rohy
    -0.71
    POSITIVE LOGITS
     it
    0.87
     this
    0.83
     anyone
    0.78
    nt
    0.73
     anybody
    0.69
    Anybody
    0.61
     everyone
    0.60
     there
    0.59
     everybody
    0.56
    Anyone
    0.56
    Activations Density 0.116%

    No Known Activations