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. 24-GEMMASCOPE-RES-16K
    6. 16382
    Prev
    Next
    INDEX
    Explanations

    clinical findings and adverse effects related to ocular health and treatments

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

    after "anterior", "significant", or "average"

    np_acts-logits-general · gemini-2.0-flash

    cornea, anterior, visual acuity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ales
    -0.55
    Betrieb
    -0.53
     rosewood
    -0.53
    HasForeignKey
    -0.52
    Изо
    -0.52
    
    -0.52
    hyrchwyd
    -0.51
    illeur
    -0.51
     grapes
    -0.51
     indisponible
    -0.51
    POSITIVE LOGITS
    cor
    0.53
     ker
    0.52
    wikidata
    0.51
    Corne
    0.51
     regra
    0.50
    __*/
    0.47
    front
    0.47
     anterior
    0.47
     Corne
    0.45
     front
    0.45
    Activations Density 0.468%

    No Known Activations