© 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. 18-GEMMASCOPE-RES-16K
    11. 3469
    Prev
    Next
    INDEX
    Explanations

    punctuation and various markers, including periods and commas, indicating sentence structure and formatting in text

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

    Follows a citation or reference

    np_acts-logits-general · gemini-2.0-flash

    authors and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.89
    GEBURTSDATUM
    -0.87
    Enllaços
    -0.79
    انجليز
    -0.77
    RTLD
    -0.74
     ComVisible
    -0.74
     مشين
    -0.74
    LayoutStyle
    -0.72
    '],$
    -0.71
    `,
    -0.70
    POSITIVE LOGITS
    J
    0.54
    PMailer
    0.52
     R
    0.49
     L
    0.48
     J
    0.48
     helft
    0.46
     et
    0.45
     A
    0.44
     C
    0.44
     B
    0.42
    Activations Density 0.079%

    No Known Activations