© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2057
    Prev
    Next
    INDEX
    Explanations

    references to systems or classifications used for organizing and categorizing entities, especially in scientific contexts

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

    Foreign language or uncommon words/phrases

    np_acts-logits-general · gemini-2.0-flash

    titles and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --
    -0.45
    .}\
    -0.44
    …,
    -0.44
    .}(
    -0.41
    ----------
    -0.41
    .}~\
    -0.41
     garg
    -0.39
    ".$_
    -0.38
    ,$_
    -0.37
     smaller
    -0.36
    POSITIVE LOGITS
     تضيفلها
    1.13
     HasFactory
    0.96
    afficheront
    0.93
    Datuak
    0.89
    djangoproject
    0.85
     Meksiku
    0.83
    expandindo
    0.83
    antMatchers
    0.83
     ویکی‌پدیا
    0.82
     ligiloj
    0.82
    Activations Density 0.185%

    No Known Activations