© 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 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. 11031
    Prev
    Next
    INDEX
    Explanations

    language related to communication and correspondence

    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
    1842
    +0.14
    0.4%
    674
    +0.13
    0.4%
    1978
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.14
    0.03
    1282
    +0.13
    0.03
    862
    +0.12
    0.03
    Negative Logits
     Gorb
    -0.83
     eiffel
    -0.79
     Bengt
    -0.78
     Sted
    -0.77
     Rine
    -0.73
     Bartholo
    -0.73
     Keny
    -0.73
     Hez
    -0.73
     Quod
    -0.73
     vété
    -0.72
    POSITIVE LOGITS
     occur
    0.59
     conosco
    0.58
     happen
    0.58
    Sucesor
    0.57
    windowFixed
    0.57
     occurred
    0.57
     exists
    0.57
     happened
    0.56
     occurs
    0.56
     exist
    0.55
    Activations Density 0.503%

    No Known Activations