© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    references to young children and their ages in years

    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
    +0.20
    0.8%
    1978
    +0.12
    0.4%
    1140
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.20
    0.04
    792
    +0.12
    0.03
    498
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.97
    ⓧ
    -0.86
     intersper
    -0.76
     nawr
    -0.58
    
    -0.56
     Numéro
    -0.56
    zeczytaj
    -0.56
    Transcripción
    -0.55
    💼
    -0.54
    <!--
    -0.53
    POSITIVE LOGITS
     idolat
    0.89
     child
    0.67
     drago
    0.67
     Sardegna
    0.66
     children
    0.66
     toddler
    0.64
     Cæsar
    0.64
     ducato
    0.63
     Jambi
    0.63
     Reggio
    0.62
    Activations Density 0.106%

    No Known Activations