© 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. 21-GEMMASCOPE-RES-16K
    11. 2389
    Prev
    Next
    INDEX
    Explanations

    mathematical statements about assumptions and their validity in proofs or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.72
     مرئيه
    -0.71
    COUVER
    -0.67
    EDEFAULT
    -0.67
    脚注の使い方
    -0.65
    aarrggbb
    -0.60
    Hentet
    -0.59
    WebVitals
    -0.59
     يتيمه
    -0.58
    ysacchar
    -0.57
    POSITIVE LOGITS
     hold
    2.23
     holds
    2.12
    hold
    1.85
     holding
    1.85
     Hold
    1.83
     HOLD
    1.73
     Holds
    1.70
    Hold
    1.67
    holds
    1.64
    HOLD
    1.64
    Activations Density 0.678%

    No Known Activations