© 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. 5817
    Prev
    Next
    INDEX
    Explanations

    ages and age-related information

    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
    1013
    +0.10
    0.3%
    554
    +0.10
    0.3%
    1978
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.10
    0.04
    825
    +0.10
    0.02
    1556
    +0.09
    0.03
    Negative Logits
     quelquefois
    -0.82
     fortn
    -0.79
     surpl
    -0.79
     »>
    -0.77
     contd
    -0.76
     intersper
    -0.76
     Hn
    -0.75
     soulign
    -0.73
     Manufact
    -0.73
     renfer
    -0.72
    POSITIVE LOGITS
     children
    0.81
    children
    0.77
     child
    0.72
    child
    0.69
     kids
    0.67
    PerformLayout
    0.65
     kid
    0.64
    Children
    0.60
     bambini
    0.59
     PeEnEo
    0.59
    Activations Density 0.150%

    No Known Activations