© 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
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 1193
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with size and type variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addGap
    -0.46
     chấm
    -0.41
    setVerticalGroup
    -0.41
    GEBURTSDATUM
    -0.41
     financiera
    -0.40
    AutoField
    -0.40
     rospy
    -0.39
    Hochspringen
    -0.38
     beginnetje
    -0.38
     Италијани
    -0.38
    POSITIVE LOGITS
     types
    0.75
     type
    0.71
    DOCTYPE
    0.63
     TYPES
    0.61
     kinds
    0.59
    GenerationType
    0.59
    getType
    0.57
     Types
    0.56
     varieties
    0.56
     getType
    0.56
    Activations Density 0.516%

    No Known Activations