© 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. 3294
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals and their roles or contributions

    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
    1741
    +0.14
    0.6%
    1535
    +0.11
    0.5%
    1343
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.14
    0.08
    1343
    +0.11
    0.08
    2025
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.50
     can
    -0.95
     has
    -0.94
     have
    -0.93
     do
    -0.90
     as
    -0.90
     to
    -0.89
     on
    -0.89
    ,
    -0.89
     for
    -0.89
    POSITIVE LOGITS
     Février
    2.38
     quoique
    2.30
     Traité
    2.24
     Décembre
    2.18
     fameux
    2.08
     Chapitre
    2.07
     Ottobre
    2.07
     nôtre
    2.05
     Luglio
    2.04
     véhic
    2.04
    Activations Density 0.406%

    No Known Activations