© 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. 16092
    Prev
    Next
    INDEX
    Explanations

    references to specific measurements, statistics, or medical conditions

    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
    674
    +0.25
    0.9%
    1967
    +0.19
    0.6%
    1150
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1819
    +0.25
    0.08
    1842
    +0.19
    0.07
    1438
    +0.17
    0.05
    Negative Logits
     effe
    -1.87
     desir
    -1.81
     nece
    -1.80
     doman
    -1.78
     fep
    -1.77
     unden
    -1.76
     illi
    -1.74
     ftu
    -1.74
     wien
    -1.74
     fuf
    -1.72
    POSITIVE LOGITS
    .
    1.08
    ;
    0.92
    ,
    0.90
    :
    0.84
    !
    0.83
     (
    0.81
    ..
    0.81
     -
    0.81
     .
    0.81
    。
    0.79
    Activations Density 0.483%

    No Known Activations