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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6148
    Prev
    Next
    INDEX
    Explanations

    references to the term "Av" and its variations, likely related to audio or video file formats and related technologies

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

    Token "av" followed by a variety of suffixes

    np_acts-logits-general · gemini-2.0-flash

    av followed by suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    subpackage
    -0.56
    awtextra
    -0.53
     TestCase
    -0.53
     CommandType
    -0.52
    lodash
    -0.52
     FormsModule
    -0.52
     polizia
    -0.51
     tetto
    -0.50
    ότε
    -0.49
     chaqueta
    -0.49
    POSITIVE LOGITS
     defaultstate
    0.71
     חיצוניים
    0.68
    клопе
    0.64
     PLWABN
    0.64
     AttributeSet
    0.63
     protoimpl
    0.58
    HandlerContext
    0.57
    DeleteBehavior
    0.57
    CloseOperation
    0.56
     av
    0.55
    Activations Density 0.093%

    No Known Activations