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. 22-GEMMASCOPE-RES-16K
    6. 10934
    Prev
    Next
    INDEX
    Explanations

    references to scheduled times and dates

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

    Times in p.m

    np_acts-logits-general · gemini-2.0-flash

    times and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.78
    StructEnd
    -0.71
    PropertyChanging
    -0.70
    RTLD
    -0.69
    ymce
    -0.68
     BoxFit
    -0.67
    ChildScrollView
    -0.65
    Gweler
    -0.65
    modelBuilder
    -0.63
     <<<<<<<<<<<<<<
    -0.62
    POSITIVE LOGITS
    handleSubmit
    0.53
     proie
    0.49
     ffilmiau
    0.46
     kokona
    0.44
     mücade
    0.43
    ServiceTest
    0.43
     prostu
    0.42
    aspectj
    0.42
     traitements
    0.42
     disampaikan
    0.42
    Activations Density 0.068%

    No Known Activations