© 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. 4185
    Prev
    Next
    INDEX
    Explanations

    references to assistance and resourcefulness in challenging situations

    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
    +0.34
    1.5%
    1967
    +0.17
    0.8%
    738
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.34
    0.10
    1967
    +0.17
    0.08
    1403
    +0.16
    0.00
    Negative Logits
    <bos>
    -2.18
    ──
    -0.66
    /*@
    -0.64
    <b>
    -0.62
    char
    -0.61
    form
    -0.60
    //----
    -0.60
    align
    -0.60
    //---
    -0.60
    //--
    -0.60
    POSITIVE LOGITS
     swarovski
    1.73
     Juf
    1.56
     reluct
    1.54
     unwarran
    1.50
     Minang
    1.47
     viciss
    1.45
     ftu
    1.45
     disagre
    1.45
     ecru
    1.44
     apprehen
    1.44
    Activations Density 1.543%

    No Known Activations