© 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. 58661
    Prev
    Next
    INDEX
    Explanations

    terms related to beauty or attractiveness

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

    splendid or slender

    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
     noDo
    -0.52
    brinco
    -0.50
    calça
    -0.50
    IntoConstraints
    -0.50
     magasiner
    -0.50
    DotNetBar
    -0.49
     UFC
    -0.49
    rsiniz
    -0.49
    الحياه
    -0.49
    /***/
    -0.48
    POSITIVE LOGITS
     splendid
    1.20
    endid
    1.05
     splendor
    0.75
     splendour
    0.71
     splend
    0.59
    wonderful
    0.57
     Wonderful
    0.55
     excellent
    0.55
     wonderful
    0.54
     świet
    0.53
    Activations Density 0.005%

    No Known Activations