© 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. 10199
    Prev
    Next
    INDEX
    Explanations

    phrases that involve a sense of measurement or quantification

    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
    #+#
    -0.74
    einer
    -0.70
     sebuah
    -0.64
    another
    -0.63
    Another
    -0.62
     einer
    -0.61
     Another
    -0.60
     einem
    -0.58
    something
    -0.57
    the
    -0.56
    POSITIVE LOGITS
     ainfi
    0.73
     afield
    0.70
    ViewFeatures
    0.66
    LookAnd
    0.65
    IsMutable
    0.62
     appunto
    0.58
    ValueStyle
    0.57
     nadzieję
    0.56
     AspNetCore
    0.55
    躇
    0.55
    Activations Density 0.489%

    No Known Activations