© 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. 38-GEMMASCOPE-RES-16K
    11. 8752
    Prev
    Next
    INDEX
    Explanations

    specific entities or people involved in legal or financial matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.45
    ỡng
    -0.43
     consultato
    -0.42
    IonicModule
    -0.41
    WebElementEntity
    -0.41
     TAMBIÉN
    -0.40
    istoitu
    -0.38
     Magist
    -0.38
    IntoConstraints
    -0.38
    Mata
    -0.37
    POSITIVE LOGITS
     Mer
    3.27
     mer
    3.20
    Mer
    3.16
     MER
    3.03
    mer
    2.72
    MER
    2.69
     MERC
    2.34
     Мер
    2.27
     merc
    2.22
     Merge
    2.20
    Activations Density 1.121%

    No Known Activations