© 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 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. 5523
    Prev
    Next
    INDEX
    Explanations

    descriptions of events or gatherings, specifically rallies

    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
    421
    +0.12
    0.4%
    938
    +0.12
    0.4%
    1092
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1351
    +0.12
    0.02
    938
    +0.12
    0.03
    1562
    +0.12
    0.02
    Negative Logits
     tind
    -0.64
     lts
    -0.63
     finis
    -0.61
     كومونز
    -0.61
     oun
    -0.59
     hoga
    -0.59
     kac
    -0.58
     aen
    -0.58
     dissi
    -0.57
     faa
    -0.57
    POSITIVE LOGITS
     rally
    1.43
     rallies
    1.25
     Rally
    1.23
    rally
    1.12
    Rally
    1.09
     rallying
    1.08
     rallied
    1.05
     Ral
    0.64
    Ral
    0.56
     împre
    0.52
    Activations Density 0.086%

    No Known Activations