Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 13915
    Prev
    Next
    INDEX
    Explanations

    references to beaches and coastal locations

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

    beaches and coastal locations

    np_acts-logits-general · gemini-2.0-flash

    beach house, beach ball, Beach Boys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.80
     Roskov
    -0.73
     beginnetje
    -0.72
     CreateTagHelper
    -0.70
     виправивши
    -0.69
    UnusedPrivate
    -0.66
     hObject
    -0.65
    ContentAsync
    -0.62
    msgTypes
    -0.62
    TagMode
    -0.60
    POSITIVE LOGITS
    side
    0.81
    comber
    0.78
    front
    0.65
    SIDE
    0.61
    routeProvider
    0.58
     resort
    0.58
     resorts
    0.55
     front
    0.54
    bree
    0.54
     Resort
    0.54
    Activations Density 0.072%

    No Known Activations