© 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. 13282
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to warranties and products

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

    ending in "ies," "ied," or "ry"

    np_acts-logits-general · gemini-2.0-flash

    words ending in ies

    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
     thiệu
    -0.43
    談社
    -0.42
    vičius
    -0.42
    éramos
    -0.42
     McIn
    -0.41
    bonucle
    -0.41
     noqa
    -0.40
    LEncoder
    -0.40
    Pome
    -0.39
     hå
    -0.39
    POSITIVE LOGITS
    ies
    1.07
    IES
    1.00
    ys
    0.97
    yship
    0.93
    yp
    0.90
    Y
    0.89
    ying
    0.87
     ies
    0.87
    ry
    0.87
    ries
    0.86
    Activations Density 0.365%

    No Known Activations