© 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. 4384
    Prev
    Next
    INDEX
    Explanations

    the word "however" indicating a contrast or contradiction

    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
    699
    +0.13
    0.4%
    1381
    +0.11
    0.4%
    2034
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.13
    0.07
    1381
    +0.11
    0.05
    1194
    +0.11
    0.04
    Negative Logits
     délib
    -0.78
     sappi
    -0.75
     doveva
    -0.75
     voleva
    -0.74
    djang
    -0.72
     persino
    -0.69
    Noice
    -0.65
    település
    -0.65
     compréhen
    -0.65
    printStats
    -0.64
    POSITIVE LOGITS
    ,
    0.61
     asmen
    0.49
     however
    0.49
    actéristique
    0.48
    مقاله
    0.47
    ،
    0.46
    However
    0.46
    Obrázky
    0.46
    ，
    0.45
    STRUCTOR
    0.45
    Activations Density 0.078%

    No Known Activations