© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 10985
    Prev
    Next
    INDEX
    Explanations

    specific programming or coding elements and structures

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

    cute and adorable descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.79
     EconPapers
    -0.75
     '\\;'
    -0.66
    IntoConstraints
    -0.64
    Personendaten
    -0.61
    новништво
    -0.58
     puissant
    -0.58
     GenerationType
    -0.57
     noDo
    -0.57
    ]")]
    -0.56
    POSITIVE LOGITS
     cute
    0.87
     adorable
    0.79
    Cute
    0.79
     Cute
    0.78
     cutest
    0.74
     Adorable
    0.72
    cute
    0.71
    Adorable
    0.70
     charming
    0.66
     lovely
    0.63
    Activations Density 0.000%

    No Known Activations