© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7346
    Prev
    Next
    INDEX
    Explanations

    medical and research-related terms

    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
    2019
    +0.14
    0.4%
    382
    +0.12
    0.4%
    1173
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1173
    +0.14
    0.04
    935
    +0.12
    0.02
    1216
    +0.09
    0.03
    Negative Logits
     milano
    -1.14
     maroc
    -1.06
     thuy
    -0.97
     tenda
    -0.95
     zucca
    -0.94
     riva
    -0.94
     sement
    -0.94
     vinci
    -0.93
     loto
    -0.92
     tomba
    -0.91
    POSITIVE LOGITS
     which
    0.83
     called
    0.73
     located
    0.71
     however
    0.71
    which
    0.68
     dubbed
    0.67
     nicknamed
    0.67
     taken
    0.65
     though
    0.65
     carried
    0.63
    Activations Density 0.152%

    No Known Activations