© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9789
    Prev
    Next
    INDEX
    Explanations

    statistical terminology related to model evaluation and performance

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

    "find" or "found"

    np_acts-logits-general · gemini-2.0-flash

    find or found

    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
     发表于
    -0.59
    GEBURTSDATUM
    -0.55
    imageshack
    -0.51
    OrNil
    -0.50
    ContentAsync
    -0.49
    oucí
    -0.49
    astéroïdes
    -0.48
    PageRoute
    -0.47
    __":
    
    -0.47
     beginnetje
    -0.47
    POSITIVE LOGITS
     found
    3.50
     find
    3.40
     finding
    3.30
    find
    3.25
     finds
    3.21
    found
    3.12
    Find
    3.04
     Find
    3.01
     Finding
    2.98
    finding
    2.96
    Activations Density 0.819%

    No Known Activations