© 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. 15394
    Prev
    Next
    INDEX
    Explanations

    instances of the term "IN" and variations of "nan."

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

    Following the letter "N"

    np_acts-logits-general · gemini-2.0-flash

    N followed by specific endings

    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
     CreateTagHelper
    -0.58
    tracked
    -0.56
    typer
    -0.54
    QMetaType
    -0.54
    dreams
    -0.53
    greens
    -0.52
    gable
    -0.52
    target
    -0.52
    track
    -0.50
    lihood
    -0.49
    POSITIVE LOGITS
    avigation
    0.55
    nın
    0.51
    ews
    0.50
    atural
    0.49
     Scen
    0.49
    umer
    0.48
    nnnn
    0.48
     Snail
    0.46
    yntaxException
    0.46
    ext
    0.46
    Activations Density 0.531%

    No Known Activations