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. 14-GEMMASCOPE-RES-16K
    6. 12764
    Prev
    Next
    INDEX
    Explanations

    terms related to ecological restoration and native species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-
    -0.59
    äischen
    -0.56
    sonic
    -0.55
    ///</
    -0.54
    rassing
    -0.53
    raught
    -0.51
    TagHelpers
    -0.51
     Ko
    -0.51
    inescent
    -0.50
    permitAll
    -0.50
    POSITIVE LOGITS
     تانيه
    0.81
     diapers
    0.66
     himo
    0.66
     cardinals
    0.65
     comigo
    0.61
    VersionUID
    0.61
     baseman
    0.60
     veterinarians
    0.60
     binoculars
    0.59
    ualitas
    0.59
    Activations Density 0.911%

    No Known Activations