© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5951
    Prev
    Next
    INDEX
    Explanations

    terms related to detection methods and processes

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

    "detect" and its variations

    np_acts-logits-general · gemini-2.0-flash

    detection of 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 @ 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
     Empres
    -0.56
     personalización
    -0.49
     Anſ
    -0.46
     année
    -0.46
    lendir
    -0.45
    Strut
    -0.45
     empres
    -0.45
     esposo
    -0.44
    RHS
    -0.44
     gü
    -0.43
    POSITIVE LOGITS
     detection
    2.00
     detect
    1.95
     Detect
    1.86
     Detection
    1.84
     detecting
    1.82
    detect
    1.80
     detected
    1.73
     detects
    1.69
    Detection
    1.66
    detection
    1.66
    Activations Density 0.227%

    No Known Activations