© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15540
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to statistical models and estimation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     incomp
    -0.37
     sheet
    -0.32
    ஊ
    -0.29
     Am
    -0.28
     joke
    -0.28
     Al
    -0.27
     Denn
    -0.27
     Mar
    -0.26
    έχ
    -0.26
     sheets
    -0.26
    POSITIVE LOGITS
     للاسماء
    0.86
     HasFactory
    0.78
     queſta
    0.69
    featureID
    0.66
     gynhyrchwyd
    0.66
     MainAxisSize
    0.65
     незавершена
    0.64
    ympto
    0.63
     ſtre
    0.63
     surla
    0.63
    Activations Density 3.011%

    No Known Activations