© 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. 10-GEMMASCOPE-RES-16K
    11. 13056
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons of best and worst performances or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    UnusedPrivate
    -0.72
    AddTagHelper
    -0.71
    StoreMessageInfo
    -0.66
     disambiguazione
    -0.66
     Trouver
    -0.66
    aarrggbb
    -0.63
    -------------</
    -0.62
    yntaxException
    -0.60
     ISNI
    -0.59
    Viitteet
    -0.58
    POSITIVE LOGITS
     sejauh
    0.50
    STRICT
    0.48
    GeneratedMessage
    0.47
    为止
    0.46
    Offshore
    0.46
     ever
    0.45
    liest
    0.45
    scalatest
    0.45
    recent
    0.45
     longest
    0.45
    Activations Density 0.322%

    No Known Activations