© 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. 321
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as classes, methods, and control structures

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

    Code snippets or image tags

    np_acts-logits-general · gemini-2.0-flash

    code prefixes or scientific terms

    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
    apimachinery
    -0.78
    =$?
    -0.77
     itſelf
    -0.74
    Vorlage
    -0.72
    — 
    -0.59
     -->>
    -0.59
     **/
    -0.59
    rovnik
    -0.58
     Codable
    -0.58
    NSIndexPath
    -0.58
    POSITIVE LOGITS
    var
    0.64
    IUrlHelper
    0.60
    LookAnd
    0.59
    new
    0.56
    SourceChecksum
    0.55
     boycot
    0.55
     boycott
    0.54
    Family
    0.51
     Family
    0.49
     test
    0.48
    Activations Density 0.107%

    No Known Activations