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. 129046
    Prev
    Next
    INDEX
    Explanations

    terms related to depth or intensity, especially in a contextual or metaphorical sense

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

    deep learning

    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
    
    -0.54
     Autorizaciones
    -0.39
     estekak
    -0.39
    WebControls
    -0.36
     ivelany
    -0.36
    Chir
    -0.35
    }`).
    -0.35
    Tracce
    -0.34
    出版年
    -0.34
     wind
    -0.34
    POSITIVE LOGITS
    deep
    2.78
     deep
    2.41
    Deep
    2.36
     Deep
    2.20
    DEEP
    2.16
    深
    2.05
     DEEP
    1.98
     deeper
    1.88
     deepest
    1.84
     глубо
    1.80
    Activations Density 0.004%

    No Known Activations