© 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. 1617
    Prev
    Next
    INDEX
    Explanations

    instances of the word "slip" and related phrases indicating loss or oversight

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

    escaping or slipping

    np_acts-logits-general · gemini-2.0-flash

    let slip

    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
    adpleegd
    -0.58
    ValueStyle
    -0.49
    tonode
    -0.48
     pamamagitan
    -0.46
     Puritans
    -0.45
     campeão
    -0.45
    hoek
    -0.43
    createStatement
    -0.42
    RenderAtEndOf
    -0.42
     gesam
    -0.42
    POSITIVE LOGITS
     escapes
    1.40
     escaped
    1.36
     escape
    1.33
     el
    1.20
     escaping
    1.15
     slip
    1.08
    escaped
    1.06
     elusive
    1.05
     Escape
    1.04
     slips
    1.04
    Activations Density 0.199%

    No Known Activations