© 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. 4339
    Prev
    Next
    INDEX
    Explanations

    higher education qualifications and areas of expertise

    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
    +0.37
    1.4%
    752
    +0.17
    0.7%
    605
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.37
    0.09
    605
    +0.17
    0.04
    16
    +0.15
    0.08
    Negative Logits
    <bos>
    -2.14
    SequentialGroup
    -0.81
     createState
    -0.80
     typelib
    -0.79
    RuleContext
    -0.73
    cshtml
    -0.73
     will
    -0.72
     continue
    -0.72
     be
    -0.72
     put
    -0.71
    POSITIVE LOGITS
     increa
    1.94
     Juf
    1.92
     affor
    1.90
     sovere
    1.89
     accla
    1.80
     reluct
    1.75
     prét
    1.74
     maneu
    1.73
     disagre
    1.72
     eiffel
    1.72
    Activations Density 0.554%

    No Known Activations