© 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. 22-GEMMASCOPE-RES-16K
    11. 11228
    Prev
    Next
    INDEX
    Explanations

    conjunctions or the use of the ampersand symbol in text

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

    HTML entity encodings

    np_acts-logits-general · gemini-2.0-flash

    ampersand connecting words

    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
    -
    -0.65
    (
    -0.63
    ,
    -0.60
    principalTable
    -0.59
    FormBuilder
    -0.57
    ニュアル
    -0.56
     bowiem
    -0.55
    üle
    -0.54
     Wiktionnaire
    -0.53
     ivelany
    -0.52
    POSITIVE LOGITS
    amp
    2.17
    ndash
    1.64
    quot
    1.54
    mdash
    1.45
    ldquo
    1.30
    nbsp
    1.10
    raquo
    1.03
    httphttps
    1.02
    rdquo
    1.01
    AMP
    1.01
    Activations Density 0.062%

    No Known Activations