© 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. 13-GEMMASCOPE-RES-16K
    6. 817
    Prev
    Next
    INDEX
    Explanations

    references to factors and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.94
    原始内容存档于
    -0.74
     LIS
    -0.72
    úsqueda
    -0.70
    edicated
    -0.70
    orgeous
    -0.69
    LIS
    -0.69
    mobileqq
    -0.69
    Hyundai
    -0.68
    ihnachten
    -0.68
    POSITIVE LOGITS
     factors
    1.73
     Factors
    1.70
     Factor
    1.56
    factors
    1.56
     FACTOR
    1.53
    Factors
    1.52
     FACTORS
    1.51
     factor
    1.44
    Factor
    1.43
    factor
    1.37
    Activations Density 0.122%

    No Known Activations