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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 504
    Prev
    Next
    INDEX
    Explanations

    financial data and calculations related to income statements and expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    muss
    -0.48
     settimana
    -0.46
    setDo
    -0.45
    ambito
    -0.45
     pido
    -0.43
    Work
    -0.43
    Conrad
    -0.42
     nawr
    -0.42
     partea
    -0.41
     quelquefois
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.78
    ngdoc
    0.67
    Démographie
    0.64
    artamento
    0.63
    NamedQueries
    0.61
     kaarangay
    0.61
    LOYD
    0.60
     RATIO
    0.60
    CreateModel
    0.58
    RATIO
    0.57
    Activations Density 0.359%

    No Known Activations