© 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. 5786
    Prev
    Next
    INDEX
    Explanations

    numerical patterns within research citations

    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
    1343
    +0.16
    0.5%
    674
    +0.15
    0.4%
    1804
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1804
    +0.16
    0.02
    1912
    +0.15
    0.02
    163
    +0.12
    0.01
    Negative Logits
     unspeak
    -1.31
     shenan
    -1.23
     impractica
    -1.14
     impra
    -1.12
     Daven
    -1.10
     disreg
    -1.04
     apprehen
    -1.04
     indescri
    -1.01
     gaily
    -1.00
     sculptured
    -0.99
    POSITIVE LOGITS
     marte
    1.16
     utop
    1.15
     Bakter
    1.11
     Kategor
    1.04
     reger
    1.02
     manuten
    1.02
     pól
    0.96
     handels
    0.96
     habet
    0.94
     solidar
    0.94
    Activations Density 0.036%

    No Known Activations