© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2392
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to studies and research

    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
    +0.39
    1.5%
    227
    +0.10
    0.4%
    764
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.39
    0.05
    5
    +0.10
    0.03
    16
    +0.09
    0.06
    Negative Logits
    <bos>
    -1.85
     ProtoMessage
    -0.77
     SIMBAD
    -0.74
    GraphicsUnit
    -0.72
    ImageContext
    -0.72
    ContentAsync
    -0.70
     €.
    -0.69
     '\\;'
    -0.69
    fristi
    -0.68
     €,
    -0.68
    POSITIVE LOGITS
     impra
    1.91
     reluct
    1.86
     accla
    1.84
     maneu
    1.83
     shenan
    1.79
     unspeak
    1.78
     uninten
    1.73
     disreg
    1.70
     disagre
    1.69
     apprehen
    1.64
    Activations Density 0.599%

    No Known Activations