© 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. 14858
    Prev
    Next
    INDEX
    Explanations

    Java annotations and related Java programming concepts

    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
    1741
    +0.16
    0.5%
    304
    +0.15
    0.5%
    876
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.16
    0.03
    304
    +0.15
    0.01
    876
    +0.15
    -0.00
    Negative Logits
     for
    -0.90
     in
    -0.87
     not
    -0.86
     to
    -0.86
     or
    -0.85
     so
    -0.85
     at
    -0.85
     an
    -0.84
     on
    -0.84
     as
    -0.84
    POSITIVE LOGITS
     meis
    2.19
     marte
    2.13
     dises
    2.11
     cannes
    2.07
     gmbh
    2.05
     lele
    2.05
     doman
    2.03
     franz
    2.00
     immen
    1.99
     mef
    1.96
    Activations Density 0.099%

    No Known Activations