© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2132
    Prev
    Next
    INDEX
    Explanations

    references to technology and platforms related to online services

    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
    +0.16
    0.6%
    227
    +0.10
    0.4%
    1842
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.12
    648
    +0.10
    0.06
    1224
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.69
     onStop
    -0.70
    álbum
    -0.63
     "..\..\..\
    -0.62
    /***
    -0.60
     وتسجيلات
    -0.60
    Também
    -0.59
     onBackPressed
    -0.59
    Ainda
    -0.58
    ///**
    -0.58
    POSITIVE LOGITS
     snoopy
    1.44
     maneu
    1.44
     impra
    1.40
     increa
    1.35
     milf
    1.30
     shenan
    1.29
     horrend
    1.27
     unspeak
    1.27
     scrat
    1.26
     affor
    1.25
    Activations Density 0.921%

    No Known Activations