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. 20-GEMMASCOPE-RES-65K
    6. 1142
    Prev
    Next
    INDEX
    Explanations

    phrases that express actions related to blame or responsibility

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

    repeated references to actions or responsibilities

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

    doing things or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opportunities
    -0.50
    Opportunities
    -0.48
     Pingback
    -0.46
     beslut
    -0.46
    IsContent
    -0.45
     hipó
    -0.44
     resources
    -0.44
    ginfo
    -0.44
     presença
    -0.43
     Opportunities
    -0.43
    POSITIVE LOGITS
     thing
    0.92
    +:+
    0.86
     work
    0.79
     THING
    0.75
     things
    0.75
    homework
    0.73
     deed
    0.73
     homework
    0.72
     job
    0.71
     THINGS
    0.70
    Activations Density 0.097%

    No Known Activations