© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11740
    Prev
    Next
    INDEX
    Explanations

    mentions of or related to child-related issues and controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    554
    +0.16
    0.6%
    1222
    +0.14
    0.5%
    1872
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.16
    0.06
    1872
    +0.14
    0.05
    908
    +0.13
    0.04
    Negative Logits
     rispond
    -0.60
    loài
    -0.56
     Voulez
    -0.56
     parlando
    -0.56
     rendono
    -0.55
     specialmente
    -0.54
     sembrano
    -0.54
     accanto
    -0.52
     perciò
    -0.51
     scopri
    -0.50
    POSITIVE LOGITS
     children
    1.17
    child
    1.15
    children
    1.14
     child
    1.13
    Children
    1.05
     Children
    1.01
    Child
    1.00
     CHILDREN
    0.98
     Child
    0.95
    CHILDREN
    0.94
    Activations Density 0.108%

    No Known Activations