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. 114161
    Prev
    Next
    INDEX
    Explanations

    terms related to light emission and display technologies

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

    light emitting devices and displays

    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
    awtextra
    -0.68
     bulb
    -0.55
    bulb
    -0.54
    Bulb
    -0.52
     <>",
    -0.52
    Lamp
    -0.50
    lamp
    -0.50
     lamp
    -0.49
     lampe
    -0.49
     LAMP
    -0.49
    POSITIVE LOGITS
    ########.
    0.50
     soundbar
    0.44
     flatter
    0.31
    +#+
    0.31
    omorphic
    0.31
    밌
    0.30
    eze
    0.30
     wanting
    0.30
     Ridge
    0.29
    uebas
    0.29
    Activations Density 0.060%

    No Known Activations