© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15358
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in academic or technical writing

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

    that indicate contrast or a change in direction

    np_acts-logits-general · gemini-2.0-flash

    transitions or contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olm
    -0.59
     despite
    -0.57
    ammen
    -0.57
     obwohl
    -0.56
     nonostante
    -0.56
    despite
    -0.54
    %=
    -0.53
     spite
    -0.53
     tartalomajánló
    -0.52
    accumulator
    -0.51
    POSITIVE LOGITS
     Conversely
    1.28
     conversely
    1.25
     natomiast
    1.22
    Conversely
    1.11
     hingegen
    1.06
     meanwhile
    1.04
     Meanwhile
    1.02
     dagegen
    1.02
     zaś
    1.01
     sebaliknya
    1.00
    Activations Density 0.501%

    No Known Activations