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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9680
    Prev
    Next
    INDEX
    Explanations

    code elements and attributes relevant to user interface layout in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.55
     nahilalakip
    -0.55
    posedge
    -0.49
    WriteBarrier
    -0.47
    Архівовано
    -0.45
     ProtoMessage
    -0.45
     leerlingen
    -0.43
     Lordships
    -0.43
    MemoryWarning
    -0.43
     fortunately
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.44
    立ち
    0.38
    素
    0.37
    zzleHttp
    0.36
     defStyleAttr
    0.36
    NewReader
    0.36
     Brice
    0.35
    wapV
    0.34
    WriteAttribute
    0.34
    TextBoxColumn
    0.33
    Activations Density 0.120%

    No Known Activations