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. 3-GEMMASCOPE-RES-16K
    6. 12300
    Prev
    Next
    INDEX
    Explanations

    open square brackets used in programming or data notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.14
     Theſe
    -1.14
     Efq
    -1.06
     iſt
    -1.06
     raiſ
    -1.05
     Reſ
    -1.04
     pleaſure
    -1.03
    ſelf
    -1.02
     himſelf
    -1.01
     Majefty
    -1.00
    POSITIVE LOGITS
     [
    0.90
    ([
    0.82
    =[
    0.70
    newArrayList
    0.68
    :[
    0.62
    }=[
    0.62
    ={[
    0.59
    [
    0.55
     Pa
    0.53
    antMatchers
    0.52
    Activations Density 0.156%

    No Known Activations