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. 13-GEMMASCOPE-RES-16K
    6. 4964
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming structure related to AngularJS applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.66
     الحره
    -0.63
    phir
    -0.62
    جموع
    -0.61
    %")
    -0.61
     confronti
    -0.60
    %</
    -0.59
    SourceChecksum
    -0.59
    ICAGO
    -0.57
    本日は
    -0.57
    POSITIVE LOGITS
    ########.
    0.57
     estekak
    0.55
    abestanden
    0.53
    fvar
    0.52
    XmlRootElement
    0.48
     Wikimedijinoj
    0.48
    TypedDataSet
    0.47
     AppBundle
    0.47
    sidemargin
    0.47
    EDEFAULT
    0.46
    Activations Density 0.234%

    No Known Activations