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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2619
    Prev
    Next
    INDEX
    Explanations

    words related to moral dilemmas and ethical conflicts.

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

    diseases and medical conditions.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to characteristics or attributes of people, places, or things, particularly when describing diversity or variety.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Word or phrase indicating prevalence or dominance

    np_acts-logits-general · gemini-2.0-flash

    subtype infections predominate

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    fjspx
    -0.49
    enumii
    -0.47
     ross
    -0.45
    мора
    -0.45
     hasattr
    -0.43
    çoise
    -0.43
    Laravel
    -0.43
    enumi
    -0.41
     ROSS
    -0.41
    Ross
    -0.40
    POSITIVE LOGITS
     abound
    1.82
     predominate
    1.69
     abounds
    1.64
     prevalent
    1.54
     dominate
    1.54
     predominant
    1.54
     dominant
    1.53
     galore
    1.47
     dominates
    1.46
    dominant
    1.45
    Activations Density 0.563%

    No Known Activations