© 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. 22-GEMMASCOPE-RES-16K
    11. 13746
    Prev
    Next
    INDEX
    Explanations

    quantitative estimations related to genetic variability and selection

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

    preceding or related to estimations

    np_acts-logits-general · gemini-2.0-flash

    numerical estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.80
    rungsseite
    -0.58
    AddTagHelper
    -0.52
    preventDefault
    -0.51
    scriptcase
    -0.50
    IndentedString
    -0.49
    lín
    -0.49
    tură
    -0.49
    cipline
    -0.49
    ">//
    -0.48
    POSITIVE LOGITS
     estimate
    2.93
     estimates
    2.87
     estimated
    2.71
     estimation
    2.53
     Estimates
    2.51
     Estimate
    2.48
    estimate
    2.40
     estimations
    2.40
     ESTIM
    2.38
     estimating
    2.37
    Activations Density 0.992%

    No Known Activations