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

    Neuronpedia

    APICircuit 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53127
    Prev
    Next
    INDEX
    Explanations

    expressions of concern about social issues

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

    party plaintiffs

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    OGND
    -0.88
    AddTagHelper
    -0.83
     defaultstate
    -0.79
     متعلقه
    -0.73
    tagHelperRunner
    -0.70
    StoryboardSegue
    -0.67
     <=",
    -0.67
    Fordítás
    -0.65
    BeginContext
    -0.64
    MigrationBuilder
    -0.64
    POSITIVE LOGITS
     concerned
    0.80
     interested
    0.75
    concerned
    0.68
    interested
    0.64
     interess
    0.58
     admirer
    0.57
     onlook
    0.56
     interesado
    0.55
     citizen
    0.54
     citizens
    0.54
    Activations Density 0.078%

    No Known Activations