© 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. 13289
    Prev
    Next
    INDEX
    Explanations

    the term "be."

    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
    406
    +0.18
    0.7%
    405
    +0.16
    0.6%
    122
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.18
    0.03
    405
    +0.16
    0.04
    47
    +0.14
    0.04
    Negative Logits
     actionMode
    -0.49
    <bos>
    -0.46
    PathParam
    -0.44
    EINVAL
    -0.43
    InvalidProtocol
    -0.43
    ContextCompat
    -0.43
    progressDialog
    -0.43
    प्त
    -0.42
     multiple
    -0.41
    ENOMEM
    -0.41
    POSITIVE LOGITS
     Bebe
    0.96
     tanong
    0.93
     malheure
    0.91
     viciss
    0.89
     habile
    0.89
    Be
    0.88
     confé
    0.87
     liev
    0.86
     geforce
    0.85
     béné
    0.84
    Activations Density 0.161%

    No Known Activations