© 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. 11495
    Prev
    Next
    INDEX
    Explanations

    various types of HTML form elements and their attributes

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

    HTML radio buttons and text input elements

    np_acts-logits-general · gemini-2.0-flash

    html input elements, especially radio

    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
    '}>
    -1.20
    ;'>
    -1.00
    "}>
    -0.96
    ']:
    -0.96
    ):
    -0.93
    "]:
    -0.89
    ]:
    -0.88
    '];?>
    -0.86
    :}
    -0.85
    ;">
    -0.85
    POSITIVE LOGITS
    "
    0.88
    ')}}"
    0.82
    ”
    0.82
    \"
    0.78
    +"'
    0.75
    ()
    0.73
    []"
    0.70
    ""
    0.68
    ''
    0.68
    addPreferredGap
    0.67
    Activations Density 0.192%

    No Known Activations