© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 16142
    Prev
    Next
    INDEX
    Explanations

    numerical representations or values in structured formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.66
    .
    -0.60
     (
    -0.56
     -
    -0.51
    <eos>
    -0.50
     –
    -0.50
     [
    -0.49
    ↵↵
    -0.47
    )][
    -0.45
    PKT
    -0.44
    POSITIVE LOGITS
     חיצוניים
    1.12
     EconPapers
    1.06
     שוליים
    1.04
    Obrázky
    1.03
     استنادى
    1.01
    protoimpl
    0.94
    存于互联网档案馆
    0.94
    rungsseite
    0.92
    StoryboardSegue
    0.92
    AccessorTable
    0.90
    Activations Density 0.436%

    No Known Activations