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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53389
    Prev
    Next
    INDEX
    Explanations

    content related to media recommendations or calls to action

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

    See also, read more

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     समीक्षक
    -0.74
     виправивши
    -0.73
     autorytatywna
    -0.69
     ddelweddau
    -0.65
    ]")]
    -0.64
     NSCoder
    -0.63
    SharedDtor
    -0.62
    JvmStatic
    -0.62
    VIAF
    -0.61
     gesteld
    -0.60
    POSITIVE LOGITS
    randomUUID
    0.51
     details
    0.48
    endphp
    0.45
     AssemblyCulture
    0.45
    続きを読む
    0.44
    Read
    0.43
     Pollut
    0.43
     Gleaner
    0.43
    <eos>
    0.43
    Portály
    0.43
    Activations Density 0.025%

    No Known Activations