© 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. 428
    Prev
    Next
    INDEX
    Explanations

    terms related to cooking and boiling processes

    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
    331
    +0.16
    0.8%
    50
    +0.15
    0.8%
    783
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.16
    0.02
    331
    +0.15
    0.02
    783
    +0.13
    0.01
    Negative Logits
    <bos>
    -2.36
    sm
    -0.67
    投
    -0.65
    rungsseite
    -0.64
    public
    -0.63
    Mr
    -0.61
    Vegeu
    -0.61
    /***
    
    -0.60
    card
    -0.60
    member
    -0.60
    POSITIVE LOGITS
     impra
    1.82
     maneu
    1.79
     unspeak
    1.79
     increa
    1.74
     excru
    1.74
     disagre
    1.70
     inconce
    1.69
     reluct
    1.66
     tolerably
    1.63
     affor
    1.62
    Activations Density 0.062%

    No Known Activations