© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4263
    Prev
    Next
    INDEX
    Explanations

    historical or medical terms and information related to health

    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
    998
    +0.20
    0.7%
    198
    +0.15
    0.5%
    599
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    998
    +0.20
    0.02
    198
    +0.15
    0.03
    184
    +0.14
    0.01
    Negative Logits
     philanth
    -0.80
     Utilisation
    -0.78
     Manufact
    -0.76
     EEU
    -0.73
     Vaugh
    -0.69
     Glou
    -0.68
     Intere
    -0.68
     Timp
    -0.66
     McLaugh
    -0.65
     cabriolet
    -0.64
    POSITIVE LOGITS
     totiž
    0.69
    Grüße
    0.67
    Dzięki
    0.62
    Bardzo
    0.59
    Glej
    0.59
    Confira
    0.57
    Gdy
    0.56
    Vezi
    0.56
    Vielleicht
    0.56
     infatti
    0.55
    Activations Density 0.195%

    No Known Activations