© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12118
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific attributes related to configuration and API requests

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

    Azure CLI commands

    np_acts-logits-general · gemini-2.0-flash

    azure cli acr commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.56
    lorette
    -0.44
     occaf
    -0.44
     Отечественной
    -0.44
     Gerber
    -0.43
    Personendaten
    -0.42
    Geographie
    -0.41
     Bache
    -0.40
    Geograf
    -0.40
    panier
    -0.39
    POSITIVE LOGITS
     oslo
    0.42
    DockStyle
    0.42
     Minaj
    0.41
    AutoScale
    0.41
     glance
    0.40
    NameInMap
    0.40
    Kjelder
    0.38
     disambiguazione
    0.36
    AddTagHelper
    0.36
    ArgumentParser
    0.36
    Activations Density 0.402%

    No Known Activations