Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10396
    Prev
    Next
    INDEX
    Explanations

    references to technical terms or concepts

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

    "Technical" followed by a field or assistance

    np_acts-logits-general · gemini-2.0-flash

    technical field and assistance

    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
    Havolalar
    -0.78
    GEBURTSDATUM
    -0.65
     BorderRadius
    -0.65
    XmlAccessorType
    -0.61
    astify
    -0.60
    antMatchers
    -0.59
     vectorielles
    -0.57
    cinogen
    -0.57
    RenderAtEndOf
    -0.56
    ZoneId
    -0.55
    POSITIVE LOGITS
    ities
    0.97
    TECHNICAL
    0.71
     TÉCNICA
    0.71
     TextAppearance
    0.70
     facie
    0.70
    ity
    0.69
    ."],
    0.64
    theless
    0.64
    *>(
    0.63
     TECHNICAL
    0.61
    Activations Density 0.112%

    No Known Activations