© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3530
    Prev
    Next
    INDEX
    Explanations

    numerical estimates or figures related to statistics and data comparisons

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

    numbers, percentages, or statistics

    np_acts-logits-general · gemini-2.0-flash

    numerical figures and percentages

    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
    HtmlAttribute
    -0.56
    WriteTagHelper
    -0.46
    gentes
    -0.39
     الرياضيه
    -0.39
    adam
    -0.39
    inSlope
    -0.38
    ResumeLayout
    -0.37
    utilisons
    -0.36
    født
    -0.36
    templateUrl
    -0.36
    POSITIVE LOGITS
     numbers
    1.62
     cifra
    1.50
     chiffre
    1.44
     figure
    1.39
     figures
    1.29
     chiffres
    1.28
    numbers
    1.26
     angka
    1.26
     cifras
    1.26
     Numbers
    1.25
    Activations Density 0.471%

    No Known Activations