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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53430
    Prev
    Next
    INDEX
    Explanations

    references to mineral types and their characteristics related to geological processes

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

    mineral types and formation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.65
    ArgumentParser
    -0.55
    Portály
    -0.55
    odenal
    -0.55
    ympto
    -0.54
    ussis
    -0.53
    levard
    -0.53
     Schall
    -0.52
    mphs
    -0.52
    yethylene
    -0.52
    POSITIVE LOGITS
     pilota
    0.58
     ambientale
    0.58
     facie
    0.58
    fois
    0.55
     Kelas
    0.54
     veio
    0.54
     typique
    0.54
    OLVED
    0.54
     вероятно
    0.54
     trasporto
    0.52
    Activations Density 0.087%

    No Known Activations