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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1551
    Prev
    Next
    INDEX
    Explanations

    details related to the specifications and features of toys or products

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

    Punctuation marks and symbols

    np_acts-logits-general · gemini-2.0-flash

    list item separators

    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
     Anſ
    -1.35
     doubtnut
    -1.32
     Efq
    -1.24
     Theſe
    -1.21
     Monfieur
    -1.19
     photolibrary
    -1.16
     Diſ
    -1.16
     Majefty
    -1.12
     Houſe
    -1.11
     ་་
    -1.10
    POSITIVE LOGITS
     -
    0.88
     /
    0.84
     «
    0.76
     „
    0.76
    <eos>
    0.75
     (
    0.74
     –
    0.71
    ↵
    0.68
     +
    0.67
    -
    0.64
    Activations Density 0.473%

    No Known Activations