© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6019
    Prev
    Next
    INDEX
    Explanations

    instances of the word "generate" and its variations, indicating a focus on the concept of generation or creation in various contexts

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

    "generate"

    np_acts-logits-general · gemini-2.0-flash

    generate

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     betweenstory
    -0.46
    StructEnd
    -0.43
     onClose
    -0.43
     NSCoder
    -0.42
     WIFE
    -0.42
    équilibre
    -0.41
     distancia
    -0.41
     Widers
    -0.41
     étro
    -0.40
     cumplimiento
    -0.39
    POSITIVE LOGITS
     generate
    1.88
     generated
    1.77
    generate
    1.76
     Generate
    1.74
     generating
    1.70
    Generate
    1.66
     generator
    1.65
     Generating
    1.64
     generates
    1.64
     generation
    1.61
    Activations Density 0.199%

    No Known Activations