© 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. 10660
    Prev
    Next
    INDEX
    Explanations

    negative contractions (like "can't" or "cannot") and expressions of inability

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

    "I can't" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    can't wait

    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
    onAttach
    -0.51
    Przypisy
    -0.48
    CppCodeGen
    -0.46
    聚
    -0.45
     חיצוניים
    -0.44
    kso
    -0.44
     Mas
    -0.44
    PRNewswire
    -0.43
     خارجية
    -0.42
    ngrx
    -0.42
    POSITIVE LOGITS
    IUrlHelper
    0.90
     wait
    0.89
     WAIT
    0.87
     للاسماء
    0.81
     believe
    0.81
     BELIEVE
    0.77
     imagine
    0.74
     seem
    0.72
     newBuilder
    0.68
     remember
    0.68
    Activations Density 0.094%

    No Known Activations