© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6459
    Prev
    Next
    INDEX
    Explanations

    quantifiable measurements or values represented as numbers and terms signifying sequences or steps

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

    Numbers or digits

    np_acts-logits-general · gemini-2.0-flash

    numbers and sequences

    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
    ChildScrollView
    -0.69
    DockStyle
    -0.61
    TargetException
    -0.61
    ArgsConstructor
    -0.58
     CrossRef
    -0.57
    annica
    -0.55
     الحره
    -0.54
    complexType
    -0.54
    מבר
    -0.53
    DMETHOD
    -0.52
    POSITIVE LOGITS
    getMenuInflater
    0.59
     <<<<<<<<<<<<<<
    0.58
    Erstellt
    0.54
    ftagPool
    0.54
    älte
    0.54
    SourceChecksum
    0.52
    urlpatterns
    0.48
     dibawah
    0.48
    кнул
    0.48
    tvguidetime
    0.48
    Activations Density 0.216%

    No Known Activations