© 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. 3961
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or procedure

    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
    +0.27
    1.4%
    281
    +0.11
    0.6%
    506
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.27
    0.04
    1451
    +0.11
    0.03
    197
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.98
    /***
    -0.65
    contentLoaded
    -0.64
     fel
    -0.60
     resourceCulture
    -0.59
     mit
    -0.57
    沈
    -0.56
    cat
    -0.55
     hit
    -0.55
     sch
    -0.55
    POSITIVE LOGITS
     maneu
    1.66
     affor
    1.60
     reluct
    1.47
     bandung
    1.47
     milano
    1.46
     shenan
    1.45
     impra
    1.44
     stockholm
    1.43
     maroc
    1.43
     disreg
    1.43
    Activations Density 0.025%

    No Known Activations