© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1446
    Prev
    Next
    INDEX
    Explanations

    references to the word "throat" or related phrases indicating throat-related actions or injuries

    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
    481
    +0.17
    1.0%
    492
    +0.16
    0.9%
    421
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.05
    1741
    +0.16
    0.01
    481
    +0.15
    0.04
    Negative Logits
    <bos>
    -1.10
    ánchez
    -0.63
     engage
    -0.59
    Giới
    -0.57
    Kích
    -0.56
    num
    -0.56
    estría
    -0.56
    Fuentes
    -0.56
    win
    -0.56
     Wikimedijinoj
    -0.55
    POSITIVE LOGITS
     perfet
    1.37
     impra
    1.31
     affor
    1.28
     casio
    1.28
     sandra
    1.24
     strick
    1.24
     snoopy
    1.19
     madonna
    1.19
     bett
    1.16
     Czechos
    1.15
    Activations Density 0.330%

    No Known Activations