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. 4677
    Prev
    Next
    INDEX
    Explanations

    technical terminology and references related to scientific analysis or procedures

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

    Code, questions, or short sentences starting with conjunctions

    np_acts-logits-general · gemini-2.0-flash

    number followed by value

    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
    InjectAttribute
    -0.94
     المعيارى
    -0.94
    otheby
    -0.88
     vPvB
    -0.88
    CloseOperation
    -0.87
     SqlCommand
    -0.87
     AspNetCore
    -0.86
    endphp
    -0.85
     AttributeSet
    -0.83
     snippetHide
    -0.83
    POSITIVE LOGITS
    <em>
    0.94
    <strong>
    0.87
    The
    0.87
    </strong>
    0.86
    ↵
    0.81
    What
    0.75
    Also
    0.74
    <u>
    0.73
     quæ
    0.73
     Phry
    0.72
    Activations Density 0.009%

    No Known Activations