© 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. 13244
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to technology and its applications

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

    ending in "-wise" or related to "wise"

    np_acts-logits-general · gemini-2.0-flash

    "-wise" or "-ally" suffixes

    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
     ModelExpression
    -0.78
    Tikang
    -0.70
    ьаж
    -0.67
    ècie
    -0.63
    IContainer
    -0.61
    BASELINE
    -0.59
    RTCF
    -0.59
    netbeans
    -0.59
     المعرف
    -0.58
    ródło
    -0.58
    POSITIVE LOGITS
     wise
    2.58
    wise
    2.47
    Wise
    1.78
    WISE
    1.70
     Wise
    1.61
     WISE
    1.59
     speaking
    1.17
     wisest
    1.09
    istically
    1.06
     wiser
    1.06
    Activations Density 0.180%

    No Known Activations