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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14677
    Prev
    Next
    INDEX
    Explanations

    instances of the word "identify" or its variations, focusing on detection and assessment of issues or populations

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

    "identify" or "detection"

    np_acts-logits-general · gemini-2.0-flash

    identifying specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nôtre
    -0.47
    sterone
    -0.44
    Penjelasan
    -0.41
    herzog
    -0.41
     setContent
    -0.40
    Pou
    -0.39
     medias
    -0.39
     représent
    -0.39
     contenido
    -0.38
    Exchange
    -0.38
    POSITIVE LOGITS
     detect
    0.84
     detection
    0.82
     detectar
    0.81
     detección
    0.80
     detecting
    0.78
     detects
    0.77
    detect
    0.75
     Detect
    0.75
     DETECT
    0.73
     Detection
    0.72
    Activations Density 0.502%

    No Known Activations