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. 16-GEMMASCOPE-RES-16K
    6. 6913
    Prev
    Next
    INDEX
    Explanations

    references to potential, possibilities, and prospects in various contexts

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

    "potential"

    np_acts-logits-general · gemini-2.0-flash

    potential and its implications

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.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
    XtraEditors
    -0.70
    basicConfig
    -0.64
    脚注の使い方
    -0.57
    reactstrap
    -0.57
     biscuits
    -0.56
     fermions
    -0.56
     Burrow
    -0.55
     Biscuits
    -0.55
     habituellement
    -0.55
     biscuit
    -0.54
    POSITIVE LOGITS
     potential
    1.23
    Potential
    1.22
     Potential
    1.21
    potential
    1.07
     potentials
    1.06
     POTENTIAL
    1.02
     potensi
    0.95
     potencial
    0.94
    潜在
    0.84
    entials
    0.83
    Activations Density 0.116%

    No Known Activations