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. 12-GEMMASCOPE-RES-16K
    6. 12243
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives that indicate a condition or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.61
     églises
    -0.60
     braccia
    -0.56
    serviceWorker
    -0.55
     colorés
    -0.55
     dataSnapshot
    -0.54
     withal
    -0.53
     pleaſure
    -0.53
     råd
    -0.52
     therefrom
    -0.51
    POSITIVE LOGITS
    +#+#
    0.72
     AssemblyCulture
    0.66
    InputBorder
    0.66
    __':
    0.65
     definitely
    0.65
    itself
    0.63
     '\\;'
    0.63
    principalTable
    0.63
    Šaltiniai
    0.62
    uidado
    0.61
    Activations Density 0.730%

    No Known Activations