© 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. 23-GEMMASCOPE-RES-16K
    11. 9364
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and names, particularly those related to specific fields and potentially articles or papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.96
    Datuak
    -0.77
     onAnimation
    -0.77
    脚注の使い方
    -0.72
     cherchés
    -0.71
    extAlignment
    -0.68
     surla
    -0.67
    expandindo
    -0.67
    CrossRef
    -0.67
    Geplaatst
    -0.66
    POSITIVE LOGITS
     AA
    0.52
     I
    0.51
    ety
    0.47
     YA
    0.46
     Fulda
    0.45
    I
    0.45
     NN
    0.44
    stringify
    0.43
    YU
    0.42
     Aleppo
    0.41
    Activations Density 0.148%

    No Known Activations