© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101916
    Prev
    Next
    INDEX
    Explanations

    instances of the word "structured" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UIImageView
    -0.47
     MonoBehaviour
    -0.44
    AppComponent
    -0.44
    (--
    -0.37
    PropertyName
    -0.37
     Tenden
    -0.37
    .~(\
    -0.36
    DatabaseError
    -0.35
     NSObject
    -0.35
    //=
    -0.35
    POSITIVE LOGITS
    Structured
    0.88
     Structured
    0.82
     structured
    0.81
    structured
    0.79
     unstructured
    0.75
     structuring
    0.69
    orithmic
    0.68
    MigrationBuilder
    0.68
    ductory
    0.66
    ardized
    0.66
    Activations Density 0.015%

    No Known Activations