© 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. 19-GEMMASCOPE-RES-16K
    11. 15585
    Prev
    Next
    INDEX
    Explanations

    names and terms related to individuals in the art and cultural scene

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.91
     surla
    -0.89
    tvguidetime
    -0.84
     IBOutlet
    -0.69
    IMPORTED
    -0.68
    erol
    -0.66
     Paglinawan
    -0.65
    addContainerGap
    -0.64
     lượt
    -0.63
    aktery
    -0.63
    POSITIVE LOGITS
     PyLong
    0.53
    IsPostBack
    0.51
    ्ह
    0.49
     induction
    0.47
     RESPONDENT
    0.44
    див
    0.43
    induction
    0.43
    eton
    0.43
    shuff
    0.43
     ricerche
    0.42
    Activations Density 0.120%

    No Known Activations