© 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. 14717
    Prev
    Next
    INDEX
    Explanations

    the presence of non-standard formatting or symbols related to mathematical equations

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

    LaTeX equation environments with equation numbers

    np_acts-logits-general · gemini-2.0-flash

    `nonumber` in equations

    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
     ſhe
    -0.72
     oock
    -0.70
     Arquivado
    -0.68
    Gweler
    -0.68
     raiſ
    -0.67
    AccessFile
    -0.65
     Beſ
    -0.65
     Emits
    -0.65
    omeness
    -0.65
     Theſe
    -0.64
    POSITIVE LOGITS
    CrossRef
    4.04
    PubMed
    0.74
    verwijspagina
    0.62
    UnusedPrivate
    0.59
     CrossRef
    0.58
    Crossref
    0.54
    脚注の使い方
    0.53
    IsContent
    0.50
    sizeCache
    0.46
     localObject
    0.46
    Activations Density 0.007%

    No Known Activations