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. 16-GEMMASCOPE-RES-16K
    6. 6404
    Prev
    Next
    INDEX
    Explanations

    markup and formatting tags within code snippets

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

    HTML tags or code snippets

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BibitemShut
    -1.06
     leaſt
    -1.02
     Eſ
    -0.97
     purpoſe
    -0.95
     Efq
    -0.91
    wiſe
    -0.91
     rhestr
    -0.91
    ſi
    -0.90
     becauſe
    -0.90
    ſelves
    -0.90
    POSITIVE LOGITS
    </em>
    1.05
    <em>
    1.03
    </strong>
    0.95
    s
    0.93
    <strong>
    0.87
    </sup>
    0.83
    </sub>
    0.82
    e
    0.82
    <i>
    0.81
    </i>
    0.81
    Activations Density 0.142%

    No Known Activations