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. 11-GEMMASCOPE-RES-16K
    6. 5745
    Prev
    Next
    INDEX
    Explanations

    topics related to specific achievements or classifications within various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kuuta
    -0.74
    Życiorys
    -0.72
    KommentareTeilen
    -0.68
    Jeografia
    -0.67
     esternos
    -0.67
    Попис
    -0.66
    aktery
    -0.64
     calendriers
    -0.64
     thiệu
    -0.63
    onViewCreated
    -0.63
    POSITIVE LOGITS
    xious
    0.56
    ſelf
    0.53
    ſelves
    0.52
    FunctionFlags
    0.50
    cillary
    0.49
    AccessorTable
    0.49
    OfThe
    0.49
     autem
    0.48
    IFORN
    0.48
    InThe
    0.47
    Activations Density 1.465%

    No Known Activations