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. 15-GEMMASCOPE-RES-16K
    6. 1815
    Prev
    Next
    INDEX
    Explanations

    conditions or thresholds related to financial or numerical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ges
    -0.55
    同様
    -0.49
    Beschreibung
    -0.49
     Völ
    -0.49
    {#
    -0.49
    Ges
    -0.48
     podob
    -0.47
     excru
    -0.46
    phos
    -0.46
     références
    -0.45
    POSITIVE LOGITS
     виправивши
    0.84
    esez
    0.78
     الرياضيه
    0.70
     PublicKey
    0.69
    IonicModule
    0.65
    ChildScrollView
    0.65
    تقاوى
    0.63
    GEBURTSDATUM
    0.62
     AssemblyCompany
    0.62
    usermodel
    0.61
    Activations Density 0.225%

    No Known Activations