© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4735
    Prev
    Next
    INDEX
    Explanations

    words indicating necessity or affirmation in statements

    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
    +0.25
    0.8%
    198
    +0.13
    0.4%
    438
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.25
    0.06
    1415
    +0.13
    0.04
    513
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.42
     betweenstory
    -0.61
    SourceChecksum
    -0.53
    Билгалдахарш
    -0.52
     enshr
    -0.52
     harmonize
    -0.50
    ,
    -0.49
    Varint
    -0.48
     汉
    -0.48
     reunite
    -0.48
    POSITIVE LOGITS
    capulco
    1.09
    :"-
    0.94
     ridu
    0.88
    GYPT
    0.87
     présidenti
    0.85
    alnız
    0.82
     tutt
    0.82
     Muhamma
    0.81
     soggior
    0.79
     tucson
    0.79
    Activations Density 0.668%

    No Known Activations