© 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. 14540
    Prev
    Next
    INDEX
    Explanations

    references to frames and their characteristics

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

    "frame" and related words

    np_acts-logits-general · gemini-2.0-flash

    frame-by-frame

    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
     chimique
    -0.57
    Smarty
    -0.55
     [*]
    -0.55
     química
    -0.54
    extAlignment
    -0.54
     chemical
    -0.53
     Chemical
    -0.52
    WebServlet
    -0.52
    chemical
    -0.50
    CompoundButton
    -0.50
    POSITIVE LOGITS
     frame
    4.19
     Frame
    3.76
    frame
    3.72
    Frame
    3.52
     frames
    3.30
     FRAME
    3.25
    FRAME
    3.06
     Frames
    2.95
     framed
    2.77
    フレーム
    2.72
    Activations Density 0.186%

    No Known Activations