© 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. 14738
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical distribution and prediction

    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
    678
    +0.13
    0.4%
    1671
    +0.10
    0.3%
    1363
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.13
    0.06
    678
    +0.10
    0.06
    270
    +0.10
    0.04
    Negative Logits
    .
    -0.76
     in
    -0.75
     and
    -0.75
     of
    -0.72
     to
    -0.72
     якості
    -0.71
     
    -0.71
     śmierci
    -0.71
     другому
    -0.70
    ,
    -0.70
    POSITIVE LOGITS
     immen
    1.91
     abbra
    1.90
     dispen
    1.89
     overla
    1.86
     ridu
    1.85
     erec
    1.81
     pessi
    1.79
     igno
    1.78
     robus
    1.77
     incess
    1.77
    Activations Density 0.243%

    No Known Activations