© 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. 3141
    Prev
    Next
    INDEX
    Explanations

    words related to abundance or variety

    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
    478
    +0.15
    0.6%
    1921
    +0.12
    0.5%
    50
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.08
    1137
    +0.12
    0.06
    2030
    +0.10
    0.04
    Negative Logits
    <bos>
    -1.92
     intersper
    -1.10
     shenan
    -1.03
     encomp
    -0.91
     adjour
    -0.88
     resear
    -0.87
     supposes
    -0.85
     endow
    -0.83
     apprehen
    -0.82
    /***
    -0.80
    POSITIVE LOGITS
    GYPT
    0.90
    cotch
    0.83
     superbes
    0.80
     mcqueen
    0.80
     tetrachloride
    0.75
    membrance
    0.75
     xPos
    0.75
     magnifiques
    0.74
    perties
    0.73
    tamount
    0.73
    Activations Density 0.661%

    No Known Activations