© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12850
    Prev
    Next
    INDEX
    Explanations

    components and syntax related to TeX or LaTeX code formatting

    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
    [:]
    -0.50
    曖昧さ回避
    -0.49
    staticmethod
    -0.48
    //</
    -0.47
     onStop
    -0.46
    ViewHolder
    -0.45
    ="#"><
    -0.44
    ResumeLayout
    -0.43
    idste
    -0.43
     ANAL
    -0.43
    POSITIVE LOGITS
     Latex
    0.66
    {\
    0.64
     vetorial
    0.62
     latex
    0.61
     termica
    0.60
    lamabad
    0.59
     TEX
    0.58
     vettoriale
    0.58
    rovnik
    0.58
    =\
    0.57
    Activations Density 1.466%

    No Known Activations