© 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. 4538
    Prev
    Next
    INDEX
    Explanations

    sections related to media coverage and press events

    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
    1013
    +0.17
    0.6%
    50
    +0.15
    0.6%
    678
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.17
    0.06
    678
    +0.15
    0.08
    1013
    +0.15
    0.08
    Negative Logits
    <bos>
    -2.40
    ⓧ
    -0.83
    HasIndex
    -0.80
    HasColumnType
    -0.73
    ControllerAdvice
    -0.71
    <!--
    -0.70
     automne
    -0.70
     jsPsych
    -0.68
    WillAppear
    -0.68
    setAuto
    -0.68
    POSITIVE LOGITS
     emphat
    2.05
     Keny
    2.04
     Minang
    2.01
     dises
    1.91
     aen
    1.90
     hcm
    1.81
     suspic
    1.80
     maneu
    1.77
     nomine
    1.75
     practition
    1.73
    Activations Density 0.581%

    No Known Activations