© 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. 1681
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and."

    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
    +0.33
    1.3%
    1133
    +0.09
    0.4%
    281
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.33
    0.04
    1446
    +0.09
    0.03
    1173
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.84
     intersper
    -1.58
     reluct
    -1.49
     inconce
    -1.40
     encomp
    -1.37
     gaily
    -1.35
     unspeak
    -1.33
     apprehen
    -1.32
     vainly
    -1.32
     disagre
    -1.28
    POSITIVE LOGITS
    NOPQRST
    0.63
    ly
    0.61
    IZONT
    0.61
    LY
    0.61
    yticks
    0.60
     useCallback
    0.60
    slidesPer
    0.59
    Chất
    0.59
    Ubicación
    0.59
    exión
    0.57
    Activations Density 0.237%

    No Known Activations