© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9057
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers in relation to various subjects and data in scientific writing

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

    "a" followed by a descriptive word

    np_acts-logits-general · gemini-2.0-flash

    quantifiers and proportions after "a"

    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
    TargetException
    -0.67
    queles
    -0.66
    LabelTagHelper
    -0.62
     onOptions
    -0.59
    cèse
    -0.58
    quela
    -0.56
    opress
    -0.54
    Hentet
    -0.53
    पया
    -0.53
    ########.
    -0.52
    POSITIVE LOGITS
     auffi
    0.67
     myſelf
    0.65
     proportion
    0.64
     variety
    0.64
    jooq
    0.64
     considerable
    0.64
     fufficient
    0.64
     ejus
    0.63
     sufficient
    0.63
     minimum
    0.61
    Activations Density 0.974%

    No Known Activations