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

    Neuronpedia

    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. 10121
    Prev
    Next
    INDEX
    Explanations

    references to specific terms or keywords related to entities, structures, and programming constructs

    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
     '\\;'
    -0.90
    NameInMap
    -0.84
    ThroughAttribute
    -0.80
    PerformLayout
    -0.74
     otomatig
    -0.73
     estekak
    -0.70
     CreateTagHelper
    -0.68
    OGND
    -0.68
     Administrativna
    -0.67
    󠁣
    -0.67
    POSITIVE LOGITS
     autrement
    0.34
     Ent
    0.32
    Ent
    0.31
    tät
    0.30
    Single
    0.29
     voulons
    0.29
     différences
    0.29
    *
    0.28
    AutoScale
    0.28
    First
    0.28
    Activations Density 0.151%

    No Known Activations