© 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. 14945
    Prev
    Next
    INDEX
    Explanations

    descriptions related to app features and possible improvements

    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
    876
    +0.15
    0.5%
    1446
    +0.12
    0.4%
    678
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.15
    0.07
    1415
    +0.12
    0.03
    1446
    +0.11
    0.03
    Negative Logits
     Khart
    -1.31
     Bartholo
    -1.24
     Keny
    -1.23
     Juf
    -1.18
     Glou
    -1.15
     Hez
    -1.11
     Shakspeare
    -1.11
     Gorb
    -1.11
     Abbé
    -1.10
     Mahomet
    -1.08
    POSITIVE LOGITS
     user
    0.74
     usability
    0.66
     users
    0.66
     kwi
    0.63
     frustra
    0.62
    fiets
    0.61
     functionality
    0.60
     ergonomic
    0.60
    bewah
    0.59
    user
    0.59
    Activations Density 0.535%

    No Known Activations