© 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. 77
    Prev
    Next
    INDEX
    Explanations

    negations and phrases expressing skepticism or criticism

    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
    +0.27
    0.9%
    581
    +0.09
    0.3%
    438
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    581
    +0.27
    0.07
    438
    +0.09
    0.06
    1643
    +0.08
    0.06
    Negative Logits
    <bos>
    -1.75
    HttpDelete
    -0.63
    complexType
    -0.63
    HttpPut
    -0.61
    /}.
    -0.60
     also
    -0.59
    displayquote
    -0.58
    .
    -0.58
    apnews
    -0.56
    }{||
    -0.55
    POSITIVE LOGITS
     affor
    1.47
     ecru
    1.42
     tupperware
    1.39
     impra
    1.36
     unlaw
    1.34
     hairc
    1.31
     increa
    1.31
     quoique
    1.31
     maneu
    1.29
     swarovski
    1.29
    Activations Density 0.620%

    No Known Activations