© 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. 9-GEMMASCOPE-RES-16K
    11. 14783
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical estimation and model fitting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    примеча
    -0.48
     present
    -0.44
     i
    -0.43
    ربای
    -0.43
    indir
    -0.42
    льзя
    -0.42
     che
    -0.42
    봉
    -0.41
    likon
    -0.41
    ronomy
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.81
     itſelf
    0.72
     FetchType
    0.65
     Jefus
    0.65
     EGL
    0.64
     MaterialApp
    0.64
     Reſ
    0.63
     myſelf
    0.63
     useParams
    0.62
     Solu
    0.60
    Activations Density 0.854%

    No Known Activations