© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 96330
    Prev
    Next
    INDEX
    Explanations

    instances of the word "advanced" in various contexts related to technology, science, or expertise

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

    advanced [noun/field]

    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
    <bos>
    -0.49
    toMatch
    -0.39
     spoon
    -0.39
     Quiero
    -0.39
    )))))
    -0.39
     Spoon
    -0.38
    getLabel
    -0.37
    spoon
    -0.37
    Nucle
    -0.36
    Hymen
    -0.36
    POSITIVE LOGITS
     advanced
    2.19
    advanced
    2.08
     Advanced
    2.06
    Advanced
    1.98
     ADVANCED
    1.83
    ADVANCED
    1.81
     avanzado
    1.48
    vanced
    1.44
     avanzada
    1.44
     avancé
    1.41
    Activations Density 0.012%

    No Known Activations