© 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. 16-GEMMASCOPE-RES-16K
    11. 8764
    Prev
    Next
    INDEX
    Explanations

    specific data keys and references related to veterinary and healthcare studies

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

    Followed by numbers/symbols

    np_acts-logits-general · gemini-2.0-flash

    limitations and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -1.14
     disambiguazione
    -1.13
     виправивши
    -1.12
     propOrder
    -1.11
    SourceChecksum
    -1.05
     فريبيس
    -1.01
     typelib
    -0.98
    +#+
    -0.97
     snippetHide
    -0.95
    #+#
    -0.95
    POSITIVE LOGITS
    EndContext
    0.46
    thâu
    0.44
     espar
    0.43
     alike
    0.42
    仕方
    0.38
    fflush
    0.38
    følgelig
    0.38
    InBytes
    0.37
    »
    0.37
     Offisielt
    0.37
    Activations Density 2.671%

    No Known Activations