© 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 EvalsExportsinterp-engineNEWAPI 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. 4877
    Prev
    Next
    INDEX
    Explanations

    content related to news articles, journalism, politics, and email addresses

    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
    +0.12
    0.3%
    752
    +0.10
    0.3%
    453
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    888
    +0.12
    0.03
    1828
    +0.10
    0.03
    1799
    +0.10
    0.02
    Negative Logits
     mahd
    -0.70
     shewn
    -0.67
     rodriguez
    -0.63
     ++)
    -0.56
     setDate
    -0.56
     gerai
    -0.55
    tổng
    -0.55
    ]--;
    -0.55
     lopez
    -0.55
     confider
    -0.54
    POSITIVE LOGITS
     déplo
    0.96
     appui
    0.95
     mémor
    0.91
     délib
    0.90
     récon
    0.85
     dévou
    0.84
     redé
    0.82
     emprunt
    0.81
     récomp
    0.81
     écout
    0.78
    Activations Density 0.061%

    No Known Activations