© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14947
    Prev
    Next
    INDEX
    Explanations

    references to specific scenes or moments in a story or movie

    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
    184
    +0.15
    0.4%
    906
    +0.14
    0.4%
    1577
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.04
    2044
    +0.14
    0.04
    334
    +0.13
    0.03
    Negative Logits
     bandung
    -1.29
     hcm
    -1.28
     maksi
    -1.25
     jaya
    -1.21
     lele
    -1.21
     Tangerang
    -1.18
     siena
    -1.16
     saar
    -1.15
     Juf
    -1.14
     dises
    -1.14
    POSITIVE LOGITS
     hilarious
    0.63
     memorable
    0.62
     highlight
    0.57
     fun
    0.55
    bardziej
    0.54
     really
    0.54
     executed
    0.54
     unforgettable
    0.53
     wow
    0.53
     świet
    0.53
    Activations Density 0.250%

    No Known Activations