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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 90423
    Prev
    Next
    INDEX
    Explanations

    specific proteins and their roles in cancer-related processes

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

    proteins and enzymes function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.70
     nahilalakip
    -0.69
    richTextPanel
    -0.67
     resourceCulture
    -0.67
     kasarigan
    -0.66
     estekak
    -0.65
     ujednoznacz
    -0.64
    EDEFAULT
    -0.62
    <unused41>
    -0.59
    <unused14>
    -0.59
    POSITIVE LOGITS
     protein
    0.57
     enzyme
    0.50
    protein
    0.47
     enzymes
    0.45
     Protein
    0.42
     proteína
    0.42
     proteins
    0.41
     PROTEIN
    0.41
    Protein
    0.40
     gene
    0.39
    Activations Density 0.791%

    No Known Activations