© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15435
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to software and programming frameworks

    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
    <eos>
    -0.63
     
    -0.55
    憾
    -0.46
    uples
    -0.46
    +#+
    -0.45
    =<?
    -0.44
     su
    -0.43
    =
    -0.42
     Al
    -0.42
    mannian
    -0.42
    POSITIVE LOGITS
    AnchorStyles
    6.38
    DockStyle
    1.70
     ExecuteAsync
    1.11
    extAlignment
    1.11
    RectangleBorder
    1.05
    IntoConstraints
    1.00
     فريبيس
    0.96
     Baillargeon
    0.96
    parsedMessage
    0.93
    abetes
    0.91
    Activations Density 0.004%

    No Known Activations