Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 7838
    Prev
    Next
    INDEX
    Explanations

    adverbs that convey intensity or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ultimately
    -1.34
     suddenly
    -1.32
     easily
    -1.30
     carefully
    -1.29
     quickly
    -1.29
     essentially
    -1.27
     eventually
    -1.26
     finally
    -1.23
     regularly
    -1.23
     constantly
    -1.22
    POSITIVE LOGITS
    UIControlState
    0.61
    Попис
    0.54
    DebuggerNonUser
    0.54
    økt
    0.52
     and
    0.51
    BarButtonItem
    0.51
    حياته
    0.50
    حياتها
    0.50
    CLUDE
    0.50
     entanto
    0.49
    Activations Density 0.535%

    No Known Activations