© 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. 0-GEMMASCOPE-RES-16K
    11. 2600
    Prev
    Next
    INDEX
    Explanations

    concepts related to general principles or overarching themes

    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
    principalColumn
    -0.64
    RenderAtEndOf
    -0.57
    IBOutlet
    -0.56
    Izvori
    -0.56
    Tikang
    -0.55
    majánló
    -0.54
    ScopeManager
    -0.53
     cassettes
    -0.52
    Tracce
    -0.52
     IBOutlet
    -0.50
    POSITIVE LOGITS
     general
    4.31
    general
    3.80
    General
    3.42
     General
    3.38
     général
    3.22
     GENERAL
    3.19
    GENERAL
    3.11
     generales
    2.88
     generale
    2.84
     générale
    2.66
    Activations Density 0.260%

    No Known Activations