© 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. 9184
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental and organizational structures, as well as their actions and outcomes

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

    Text preceding "including"

    np_acts-logits-general · gemini-2.0-flash

    listing items or examples

    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
     stb
    -0.51
    ArgsConstructor
    -0.50
    のように
    -0.47
    TextAppearance
    -0.47
    ்கு
    -0.47
    llary
    -0.47
     (%)
    -0.46
    amaño
    -0.45
    anum
    -0.45
    ように
    -0.44
    POSITIVE LOGITS
     including
    3.88
     Including
    3.39
    Including
    3.28
    including
    3.26
     INCLUDING
    3.00
     incluindo
    2.92
     incluyendo
    2.86
    包括
    2.66
     включая
    2.65
    INCLUDING
    2.56
    Activations Density 1.038%

    No Known Activations