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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10827
    Prev
    Next
    INDEX
    Explanations

    various causes and contributing factors related to health and nutrition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phem
    -0.61
    lemented
    -0.56
     européennes
    -0.56
    őle
    -0.51
     hindurch
    -0.51
    Interface
    -0.50
     snippetHide
    -0.50
    kezik
    -0.50
    新的
    -0.49
     gebra
    -0.49
    POSITIVE LOGITS
     causes
    1.33
     Causes
    1.29
     factors
    1.28
    Causes
    1.27
     reasons
    1.22
    causes
    1.19
     cause
    1.17
     Factors
    1.16
     causas
    1.16
    cause
    1.05
    Activations Density 0.418%

    No Known Activations