© 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. 4788
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and establishments

    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
    1385
    +0.18
    0.6%
    906
    +0.14
    0.5%
    738
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.18
    0.03
    1385
    +0.14
    0.05
    906
    +0.13
    -0.01
    Negative Logits
     consommate
    -0.66
     reconno
    -0.62
     gild
    -0.61
     emphat
    -0.60
     celtic
    -0.60
     bourg
    -0.60
     nicolas
    -0.59
     Strukt
    -0.59
     hobo
    -0.59
     eduardo
    -0.56
    POSITIVE LOGITS
     rooms
    0.71
     upstairs
    0.63
     room
    0.61
     downstairs
    0.59
     spacious
    0.59
     floors
    0.58
     floor
    0.57
     seating
    0.57
     Rooms
    0.56
    Upstairs
    0.56
    Activations Density 0.607%

    No Known Activations