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. 22-GEMMASCOPE-RES-16K
    6. 11067
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving left and right parentheses or brackets

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

    Follows "left" or a bracket

    np_acts-logits-general · gemini-2.0-flash

    left followed by delimiters

    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
     Houſe
    -1.07
     houſe
    -1.02
     Efq
    -1.01
     فريبيس
    -1.01
     lenker
    -1.00
    oredCriteria
    -0.95
    AddTagHelper
    -0.93
    хьтан
    -0.92
     Anſ
    -0.91
     Monfieur
    -0.91
    POSITIVE LOGITS
    (
    0.48
    [
    0.48
     V
    0.44
     am
    0.42
    ((
    0.42
     [
    0.41
    мато
    0.41
    teo
    0.40
     
    0.40
     ứng
    0.40
    Activations Density 0.272%

    No Known Activations