© 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. 22-GEMMASCOPE-RES-16K
    11. 13636
    Prev
    Next
    INDEX
    Explanations

    repeated phrases that emphasize context or additional information

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

    "By the" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    by the way, time, name

    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
     saken
    -0.52
    ینت
    -0.46
    VersionUID
    -0.44
    indd
    -0.44
     inuti
    -0.42
     viviendas
    -0.41
    집
    -0.41
    続
    -0.40
     snippetHide
    -0.40
    quilo
    -0.39
    POSITIVE LOGITS
     means
    1.26
     biais
    1.15
    means
    1.11
     dint
    1.09
     virtue
    1.07
     Means
    1.01
     MEANS
    0.97
    Means
    0.92
    rungsseite
    0.85
    grà
    0.83
    Activations Density 0.182%

    No Known Activations