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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10494
    Prev
    Next
    INDEX
    Explanations

    concepts related to physical phenomena and their explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    <bos>
    -0.66
    IsMutable
    -0.61
    groom
    -0.53
    BASELINE
    -0.51
     flared
    -0.51
    edema
    -0.50
     Professional
    -0.50
     informant
    -0.50
    rowsiness
    -0.50
    ärsk
    -0.49
    POSITIVE LOGITS
     billions
    0.96
    Scientists
    0.83
     Scientists
    0.83
     scientists
    0.81
     physicists
    0.77
     milliards
    0.77
     trillion
    0.72
     molecular
    0.69
     millions
    0.68
     laws
    0.67
    Activations Density 0.941%

    No Known Activations