© 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. 2208
    Prev
    Next
    INDEX
    Explanations

    information about a specific movie or entertainment franchise

    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
    50
    +0.21
    0.7%
    1577
    +0.17
    0.6%
    394
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    911
    +0.21
    0.06
    882
    +0.17
    0.12
    455
    +0.15
    -0.00
    Negative Logits
     !...
    -1.02
     effe
    -0.97
     ftu
    -0.90
     encre
    -0.89
     fto
    -0.89
     thut
    -0.88
     :)))
    -0.88
     nece
    -0.87
     inder
    -0.87
     aen
    -0.87
    POSITIVE LOGITS
     someday
    0.74
     tomorrow
    0.63
     next
    0.59
     soon
    0.59
     future
    0.58
     possibly
    0.58
     sooner
    0.56
     Possibly
    0.54
    Possibly
    0.53
     potentially
    0.51
    Activations Density 6.175%

    No Known Activations