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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1759
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns, particularly names and places, often accompanied by characteristic diacritics

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

    followed by country/city endings

    np_acts-logits-general · gemini-2.0-flash

    Šeduva, Škoda, Rashkovetsky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.61
     AttributeSet
    -0.53
    %)$
    -0.52
     Paramount
    -0.48
    ")"
    -0.47
     Paglinawan
    -0.46
    templateUrl
    -0.46
     keyCode
    -0.45
    Distribución
    -0.42
    úmer
    -0.42
    POSITIVE LOGITS
     مشين
    0.76
     cherchés
    0.72
    tvguidetime
    0.60
    er
    0.59
     referenties
    0.58
    Források
    0.58
    Skocz
    0.57
     оригіналу
    0.57
    EndGlobalSection
    0.56
     transfieras
    0.56
    Activations Density 0.119%

    No Known Activations