© 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. 14914
    Prev
    Next
    INDEX
    Explanations

    references to media coverage or commentary

    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
    198
    +0.09
    0.3%
    1535
    +0.07
    0.2%
    109
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    613
    +0.09
    0.05
    109
    +0.07
    0.05
    136
    +0.07
    0.03
    Negative Logits
     swarovski
    -1.11
     matel
    -1.02
     broderie
    -1.01
     Chapitre
    -1.01
     milano
    -1.00
     Février
    -0.97
     vété
    -0.97
     tricot
    -0.97
     Ename
    -0.95
     Pièces
    -0.94
    POSITIVE LOGITS
     news
    0.71
     coverage
    0.66
     newspapers
    0.63
     reporting
    0.63
     reports
    0.62
     reporters
    0.61
     headlines
    0.61
     newspaper
    0.59
    news
    0.58
     media
    0.58
    Activations Density 0.445%

    No Known Activations