© 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. 3144
    Prev
    Next
    INDEX
    Explanations

    questions that begin with "What is" or phrases indicating inquiry

    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
    +0.30
    1.3%
    468
    +0.10
    0.5%
    1451
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.30
    0.04
    920
    +0.10
    0.04
    468
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.39
    Autoritní
    -0.69
    例文帳に追加
    -0.60
    ⓧ
    -0.59
    ///**
    -0.54
     onPostExecute
    -0.51
     fechar
    -0.51
     GeoNames
    -0.50
     conferir
    -0.50
    Comun
    -0.50
    POSITIVE LOGITS
     Minang
    1.23
     véhic
    1.19
     Juf
    1.11
     Châ
    1.05
     mezza
    1.05
     fatis
    1.04
     accla
    1.03
     tramont
    1.03
     fua
    1.03
     socie
    1.02
    Activations Density 0.087%

    No Known Activations