© 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. 13351
    Prev
    Next
    INDEX
    Explanations

    statistics with decimal numbers

    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
    1177
    +0.14
    0.4%
    184
    +0.14
    0.4%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.14
    0.05
    1343
    +0.14
    0.05
    1486
    +0.11
    0.03
    Negative Logits
     gaily
    -0.95
     homeward
    -0.89
    <bos>
    -0.88
     reconno
    -0.81
     shenan
    -0.76
     superint
    -0.74
     endeavouring
    -0.73
     apprehen
    -0.73
     Grecian
    -0.72
     depic
    -0.71
    POSITIVE LOGITS
     quidem
    0.78
     potest
    0.76
     habet
    0.70
     quibus
    0.69
    ]$}
    0.66
     Puoi
    0.64
     eorum
    0.63
     quos
    0.62
     atque
    0.62
     sapat
    0.60
    Activations Density 0.185%

    No Known Activations