© 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. 13417
    Prev
    Next
    INDEX
    Explanations

    descriptions of the appearance and physical attributes of objects or entities

    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
    752
    +0.12
    0.4%
    1535
    +0.11
    0.3%
    674
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.12
    0.04
    1262
    +0.11
    0.04
    732
    +0.11
    0.04
    Negative Logits
     accanto
    -0.84
     quegli
    -0.79
     seoul
    -0.77
     bangkok
    -0.76
     autunno
    -0.76
     virtù
    -0.74
     venice
    -0.74
     ciasc
    -0.72
     orlando
    -0.71
     alaska
    -0.71
    POSITIVE LOGITS
    Cuen
    0.64
     terms
    0.57
     order
    0.52
     in
    0.52
     In
    0.51
    Lla
    0.51
     granada
    0.50
     Tercera
    0.50
    Perd
    0.50
    Río
    0.50
    Activations Density 0.217%

    No Known Activations