© 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. 20-GEMMASCOPE-RES-16K
    11. 3939
    Prev
    Next
    INDEX
    Explanations

    HTML header tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML or code-related syntax and tags.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extranjera
    -0.34
     hablado
    -0.32
     prohibido
    -0.31
     Calidad
    -0.28
     Embaj
    -0.27
     tố
    -0.27
     guardado
    -0.26
     Forschungs
    -0.26
    keep
    -0.25
     tumba
    -0.25
    POSITIVE LOGITS
    SequentialGroup
    9.81
    complexContent
    1.39
     CreateTagHelper
    1.25
    ParallelGroup
    1.19
    Personendaten
    1.18
    SharedCtor
    1.13
    ValueStyle
    1.12
    MigrationBuilder
    1.12
    httphttps
    1.12
    ScopeManager
    1.10
    Activations Density 0.000%

    No Known Activations