© 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. 34-GEMMASCOPE-RES-16K
    11. 327
    Prev
    Next
    INDEX
    Explanations

    programming structure elements, such as access modifiers and braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initWith
    -0.33
    GenerationType
    -0.31
    Slf
    -0.30
    expandindo
    -0.29
     HOLD
    -0.28
    pulumi
    -0.28
    viewDidLoad
    -0.28
    AppMethodBeat
    -0.28
    textAppearance
    -0.28
     ToString
    -0.28
    POSITIVE LOGITS
    private
    1.37
     private
    1.30
     PRIVATE
    1.05
     Private
    1.04
    Private
    0.99
     privado
    0.96
    PRIVATE
    0.94
     privaten
    0.93
     privately
    0.93
     privé
    0.92
    Activations Density 0.102%

    No Known Activations