© 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 - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 1215
    Prev
    Next
    INDEX
    Explanations

    the term "concept" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.69
    +#+
    -0.63
    WebElementEntity
    -0.61
     Jug
    -0.59
     Installation
    -0.57
    bootstrapcdn
    -0.57
     Installations
    -0.57
     Dates
    -0.56
     Ball
    -0.54
     installation
    -0.54
    POSITIVE LOGITS
    概念
    0.71
     conceptual
    0.71
    Concepts
    0.70
    CONCEPT
    0.68
     Concepts
    0.68
    Concept
    0.68
     conceptually
    0.66
     CONCEPTS
    0.65
     concept
    0.65
     concepts
    0.63
    Activations Density 0.288%

    No Known Activations