© 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. 7490
    Prev
    Next
    INDEX
    Explanations

    words related to technical specifications and physical descriptions, such as "backlit," "bright," "fucking bright," and "blinding light."

    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
    121
    +0.11
    0.3%
    1385
    +0.10
    0.3%
    906
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.11
    0.04
    121
    +0.10
    0.05
    455
    +0.10
    0.01
    Negative Logits
     emphat
    -0.86
     Cfr
    -0.83
     seiz
    -0.80
     fuf
    -0.77
     madonna
    -0.77
     gild
    -0.76
     beaute
    -0.76
     jil
    -0.76
     unden
    -0.75
     pite
    -0.74
    POSITIVE LOGITS
     lighting
    0.83
     illumination
    0.82
     light
    0.79
     lights
    0.77
     brightness
    0.73
     darkness
    0.70
    light
    0.70
     sunlight
    0.68
    lights
    0.66
     lamps
    0.66
    Activations Density 0.375%

    No Known Activations