© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals and cultural references

    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
    +0.12
    0.5%
    1842
    +0.10
    0.4%
    198
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.10
    138
    +0.10
    0.08
    648
    +0.10
    0.06
    Negative Logits
    <bos>
    -1.90
     ২০১
    -0.67
    displayquote
    -0.60
    sizeCache
    -0.59
    HasIndex
    -0.59
    //@
    -0.58
    github
    -0.58
    ScopeManager
    -0.58
    usercontent
    -0.58
    osoba
    -0.58
    POSITIVE LOGITS
     maneu
    1.33
     Juf
    1.29
     milf
    1.25
     Mejía
    1.20
     jurassic
    1.19
     stockholm
    1.17
     increa
    1.17
     uchiha
    1.16
     jorge
    1.15
     invin
    1.15
    Activations Density 0.743%

    No Known Activations