© 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. 13470
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize contrasts or differences

    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
    421
    +0.12
    0.4%
    605
    +0.12
    0.4%
    11
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.12
    0.03
    781
    +0.12
    0.03
    421
    +0.11
    0.03
    Negative Logits
     depic
    -0.67
     increa
    -0.66
     excru
    -0.64
     pourrais
    -0.61
     indestru
    -0.58
     Cuen
    -0.58
     prends
    -0.56
     inev
    -0.56
     guarante
    -0.56
     strick
    -0.56
    POSITIVE LOGITS
    different
    0.73
    Different
    0.70
     Different
    0.68
    Hentet
    0.68
     different
    0.66
     DIFFERENT
    0.65
     كومونز
    0.64
     differently
    0.61
    richTextPanel
    0.60
    MessageOf
    0.57
    Activations Density 0.087%

    No Known Activations