© 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. 14779
    Prev
    Next
    INDEX
    Explanations

    descriptions of tasks or activities

    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
    856
    +0.10
    0.3%
    776
    +0.10
    0.3%
    1485
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    856
    +0.10
    0.04
    776
    +0.10
    0.05
    1207
    +0.08
    0.04
    Negative Logits
     gaily
    -0.92
     plenti
    -0.90
     vainly
    -0.86
     beaute
    -0.85
     unspeak
    -0.84
     wherea
    -0.83
     tolerably
    -0.82
     shenan
    -0.81
     Augu
    -0.78
     depic
    -0.77
    POSITIVE LOGITS
     yogur
    0.62
     kür
    0.59
     tuong
    0.57
     ideolog
    0.57
     nhanh
    0.56
     funghi
    0.56
    capulco
    0.55
     quick
    0.55
     breve
    0.55
     months
    0.55
    Activations Density 0.224%

    No Known Activations