© 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. 3383
    Prev
    Next
    INDEX
    Explanations

    occurrences of numeric references and dates

    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
    +0.18
    1.1%
    251
    +0.13
    0.8%
    1978
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.18
    0.06
    321
    +0.13
    0.05
    251
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.84
     تانيه
    -0.85
    ⓧ
    -0.71
    ⏪
    -0.69
    
    -0.68
    Cyfarwyddwr
    -0.68
    المكان
    -0.62
    Пло
    -0.61
    msgTypes
    -0.61
    bibnamefont
    -0.60
    POSITIVE LOGITS
     maneu
    1.46
     maroc
    1.24
     meis
    1.23
     stockholm
    1.19
     impra
    1.18
     reluct
    1.18
     wien
    1.17
     strick
    1.16
     perfet
    1.11
     Eighteen
    1.11
    Activations Density 0.072%

    No Known Activations