© 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. 18-GEMMASCOPE-RES-16K
    11. 14286
    Prev
    Next
    INDEX
    Explanations

    error messages related to image handling in a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before/related to locations

    np_acts-logits-general · gemini-2.0-flash

    Lithuania and Šeduva

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    šanu
    -0.72
     vaiz
    -0.71
     raiſ
    -0.68
     pleaſure
    -0.68
    ėmis
    -0.68
     Theſe
    -0.67
     purpoſe
    -0.66
    vriende
    -0.66
     jūs
    -0.66
    šanai
    -0.65
    POSITIVE LOGITS
    KommentareTeilen
    0.59
    Lithuan
    0.55
     useEffect
    0.54
     Lithuania
    0.54
    onedDateTime
    0.53
     Baltic
    0.52
     disambiguazione
    0.52
     Lithuanian
    0.52
    !*\
    0.52
    artifactId
    0.51
    Activations Density 0.029%

    No Known Activations