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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6898
    Prev
    Next
    INDEX
    Explanations

    headings and structural HTML elements used for organizing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.90
    StoryboardSegue
    -0.86
     Efq
    -0.76
    neſs
    -0.74
    SBATCH
    -0.73
     faſt
    -0.72
     uſe
    -0.72
     Majefty
    -0.72
     doubtnut
    -0.71
     Shakspeare
    -0.70
    POSITIVE LOGITS
    <h2>
    2.86
    <h4>
    1.89
    <h3>
    1.88
    <h1>
    1.67
    <h5>
    1.63
    <h6>
    1.62
    <strong>
    1.27
    <u>
    1.17
    ↵
    1.12
    <b>
    1.09
    Activations Density 0.004%

    No Known Activations