© 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. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 274
    Prev
    Next
    INDEX
    Explanations

    words and phrases that imply provocation or incitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    1.1%
    528
    +0.12
    0.5%
    680
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1142
    +0.24
    0.03
    1140
    +0.12
    0.04
    353
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.72
    public
    -0.72
    protected
    -0.69
    try
    -0.69
    @
    -0.69
     she
    -0.67
    -
    -0.66
    PMailer
    -0.66
    ///
    -0.65
     went
    -0.65
    POSITIVE LOGITS
     stockholm
    2.07
     aen
    1.99
     fta
    1.96
     thut
    1.95
     affor
    1.92
     squa
    1.90
     Juf
    1.88
     desir
    1.83
     fte
    1.82
     ftu
    1.82
    Activations Density 0.176%

    No Known Activations