© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3568
    Prev
    Next
    INDEX
    Explanations

    references to public entities and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.86
    rungsseite
    -0.86
    ValueStyle
    -0.85
     littéraire
    -0.81
    NameInMap
    -0.79
     resultCode
    -0.77
    KZ
    -0.76
    RunWith
    -0.76
     interpreters
    -0.74
    ModelSerializer
    -0.71
    POSITIVE LOGITS
     Public
    1.41
    Public
    1.28
     PUBLIC
    1.25
     public
    1.21
    PUBLIC
    1.19
    public
    1.12
    blic
    1.00
    UBLIC
    0.97
    ublic
    0.96
    publica
    0.96
    Activations Density 0.072%

    No Known Activations