© 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. 13442
    Prev
    Next
    INDEX
    Explanations

    the presence of specific document structure markers like beginning-of-sequence tokens

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    light to irradiate

    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
    icolon
    -0.71
    antart
    -0.67
     gawas
    -0.65
     kasarigan
    -0.63
     ChromeDriver
    -0.63
    ]")]
    -0.62
     });
    
    -0.61
    Santis
    -0.60
     createSprite
    -0.60
    IntoConstraints
    -0.60
    POSITIVE LOGITS
     Dicapai
    0.46
     which
    0.46
     dalamnya
    0.42
    DisplayMetrics
    0.41
     pinggang
    0.41
     ya
    0.41
    ào
    0.41
    TRAILING
    0.41
     ("
    0.41
     неза
    0.40
    Activations Density 0.033%

    No Known Activations