© 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. 7021
    Prev
    Next
    INDEX
    Explanations

    movie trailers

    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
    303
    +0.18
    0.7%
    866
    +0.17
    0.6%
    161
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    866
    +0.18
    0.02
    303
    +0.17
    0.02
    1622
    +0.13
    0.01
    Negative Logits
     peppa
    -0.75
     roth
    -0.74
     madonna
    -0.74
     nicolas
    -0.73
     jacques
    -0.70
     alberto
    -0.70
     isabel
    -0.70
     venice
    -0.69
     pablo
    -0.68
     gabriel
    -0.68
    POSITIVE LOGITS
     trailer
    1.49
    trailer
    1.40
     trailers
    1.32
     Trailer
    1.31
    Trailer
    1.26
    TRAIL
    1.01
     Trailers
    0.99
     trail
    0.95
    trail
    0.92
     Trail
    0.82
    Activations Density 0.091%

    No Known Activations