© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    associations and correlations in scientific research data

    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
    +0.21
    0.8%
    1499
    +0.14
    0.6%
    876
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.21
    0.11
    876
    +0.14
    -0.02
    736
    +0.14
    0.08
    Negative Logits
    <bos>
    -2.31
     get
    -0.72
     do
    -0.71
    ,
    -0.69
     far
    -0.69
     don
    -0.69
     prepare
    -0.69
    就
    -0.67
     continue
    -0.67
     let
    -0.67
    POSITIVE LOGITS
     maneu
    2.40
     accla
    2.30
     disagre
    2.27
     effe
    2.23
     increa
    2.21
     emphat
    2.15
     affor
    2.12
     guarante
    2.12
     stockholm
    2.06
     perfet
    2.04
    Activations Density 1.000%

    No Known Activations