© 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. 118
    Prev
    Next
    INDEX
    Explanations

    references to string resources in code

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

    Strings and labels in code or configuration files

    np_acts-logits-general · gemini-2.0-flash

    strings in Android resources

    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
    ViewFeatures
    -0.65
    FailureListener
    -0.60
    UserScript
    -0.55
    postdata
    -0.53
    webElement
    -0.51
    følgelig
    -0.50
    exels
    -0.50
     henvisninger
    -0.48
    FieldBuilder
    -0.47
    CompleteListener
    -0.47
    POSITIVE LOGITS
     phrases
    0.81
     phrase
    0.79
     lbl
    0.75
    ValueStyle
    0.74
     warning
    0.73
     wording
    0.69
     title
    0.69
     label
    0.69
    lbl
    0.68
    label
    0.68
    Activations Density 0.276%

    No Known Activations