Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8680
    Prev
    Next
    INDEX
    Explanations

    specific terms related to research methodologies and clinical trials

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

    Preceding words of specific nouns

    np_acts-logits-general · gemini-2.0-flash

    list items paired with context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.67
    jsxFileName
    -0.60
    Kjelder
    -0.60
    Hozzáférés
    -0.58
     Roskov
    -0.58
    pædia
    -0.58
    useNewUrlParser
    -0.56
    posedge
    -0.55
    Šaltiniai
    -0.54
    Referències
    -0.54
    POSITIVE LOGITS
     يتيمه
    1.07
     traditionnels
    0.80
     enfans
    0.79
    aarrggbb
    0.76
     Monfieur
    0.72
     houſe
    0.72
     BoxDecoration
    0.70
    ſelf
    0.70
     feroit
    0.70
     avoient
    0.69
    Activations Density 1.448%

    No Known Activations