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. 19-GEMMASCOPE-RES-16K
    6. 2074
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court proceedings and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknownFields
    -0.77
    BibitemShut
    -0.58
     $_"
    -0.54
    bibinfo
    -0.53
    bibfield
    -0.52
    mId
    -0.51
    انتهای
    -0.50
    ^(@)
    -0.50
     Monfieur
    -0.47
     Shakspeare
    -0.47
    POSITIVE LOGITS
    帖最后由
    0.74
    MemoryWarning
    0.71
    XmlAccessType
    0.69
     AssemblyCulture
    0.66
     ModelExpression
    0.63
    orsese
    0.60
    prefixer
    0.60
    fetchone
    0.60
     ujednoznacz
    0.60
    kuuta
    0.59
    Activations Density 0.508%

    No Known Activations