© 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. 6504
    Prev
    Next
    INDEX
    Explanations

    punctuation and certain structural elements in text

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

    enumerated lists

    np_acts-logits-general · gemini-2.0-flash

    list markers

    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
    <eos>
    -0.66
    ↵
    -0.57
    .
    -0.56
     '
    -0.53
    var
    -0.52
    _
    -0.52
     var
    -0.49
    ↵↵
    -0.49
     kan
    -0.47
     all
    -0.47
    POSITIVE LOGITS
     surla
    1.46
    StoryboardSegue
    1.21
    ArrowToggle
    1.19
    ConstraintMaker
    1.13
    __':
    1.12
     disambiguazione
    1.12
     שוליים
    1.10
    setVerticalGroup
    1.08
     saites
    1.05
    __":
    1.03
    Activations Density 0.254%

    No Known Activations