© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8558
    Prev
    Next
    INDEX
    Explanations

    headings, section titles, and navigation elements related to website content and documentation

    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
    InstanceState
    -0.55
     (
    -0.51
    tagHelperRunner
    -0.50
    tojas
    -0.48
     tot
    -0.47
    Kjelder
    -0.46
     be
    -0.45
     ProtoMessage
    -0.45
    ainya
    -0.44
    oneofs
    -0.44
    POSITIVE LOGITS
     itſelf
    0.80
     myſelf
    0.78
     himſelf
    0.72
     Efq
    0.71
     iſt
    0.70
     themſelves
    0.68
     postulates
    0.67
    spesies
    0.67
     doubtnut
    0.66
    ſelf
    0.65
    Activations Density 0.450%

    No Known Activations