© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1749
    Prev
    Next
    INDEX
    Explanations

    phrases that describe conditions, requirements, or parameters related to systems or processes

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

    the neuron responds to words that express necessity, emphasis, or strong focus (tokens like require/need/for/so/many/everything/want).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.61
    <
    -0.54
    [
    -0.50
    :
    -0.47
    <bos>
    -0.47
    ↵↵
    -0.43
    Z
    -0.43
    B
    -0.42
    ↵
    -0.41
    <h2>
    -0.41
    POSITIVE LOGITS
    }")
    
    1.08
    ")));
    
    1.08
     betweenstory
    1.06
    )");
    
    1.06
     مرئيه
    1.05
    WithIOException
    1.01
    ])));
    1.01
    '))
    
    1.00
    "])
    
    1.00
     }}"></
    0.99
    Activations Density 1.254%

    No Known Activations