© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1596
    Prev
    Next
    INDEX
    Explanations

    dimensions and sizes

    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
    +0.24
    1.0%
    752
    +0.11
    0.5%
    1842
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.24
    0.04
    1352
    +0.11
    0.03
    82
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.28
     Paglinawan
    -0.79
    EndProject
    -0.76
    ROLS
    -0.73
    contentLoaded
    -0.73
    styleType
    -0.71
     onCreateView
    -0.70
     GeoNames
    -0.70
    .}(
    -0.70
    usermodel
    -0.69
    POSITIVE LOGITS
     soulign
    1.46
     véhic
    1.32
     maneu
    1.32
    dison
    1.24
     considér
    1.24
     eiffel
    1.23
     affor
    1.23
     disreg
    1.22
     fameux
    1.20
     vété
    1.20
    Activations Density 0.109%

    No Known Activations