© 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. 5699
    Prev
    Next
    INDEX
    Explanations

    terms related to project management and assignment assistance

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

    preceding special characters

    np_acts-logits-general · gemini-2.0-flash

    financial or medical terms

    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
    UpInside
    -0.58
    اریخ
    -0.53
    TargetApi
    -0.44
    <eos>
    -0.42
    撰文
    -0.40
    o
    -0.40
    Demografia
    -0.39
     
    -0.38
    いていた
    -0.37
     Приступљено
    -0.36
    POSITIVE LOGITS
    Datuak
    0.87
    tvguidetime
    0.79
     Efq
    0.72
     ſch
    0.69
    stap
    0.65
    lemish
    0.65
     whoſe
    0.65
     Conſ
    0.65
     meriva
    0.65
     Inſ
    0.64
    Activations Density 0.102%

    No Known Activations