© 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. 3454
    Prev
    Next
    INDEX
    Explanations

    keywords related to regulations and compliance in various contexts

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

    Precedes a verb in the infinitive form

    np_acts-logits-general · gemini-2.0-flash

    state followed by being

    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
     can
    -0.84
     are
    -0.82
     is
    -0.81
     could
    -0.80
     would
    -0.79
     will
    -0.77
     zouden
    -0.75
     may
    -0.74
     might
    -0.71
     was
    -0.68
    POSITIVE LOGITS
     be
    1.29
     become
    0.76
     prove
    0.73
     være
    0.71
    enterOuterAlt
    0.70
     olla
    0.70
     бути
    0.69
    NameInMap
    0.68
    VersionUID
    0.67
     cauſe
    0.67
    Activations Density 0.419%

    No Known Activations