© 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. 5766
    Prev
    Next
    INDEX
    Explanations

    locations and venues related to San Francisco

    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
    889
    +0.16
    0.6%
    168
    +0.14
    0.5%
    1757
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.16
    0.03
    168
    +0.14
    0.03
    545
    +0.12
    0.03
    Negative Logits
     reluct
    -0.69
     ingrat
    -0.69
     Egli
    -0.68
    Sklici
    -0.67
     pamph
    -0.66
     anzi
    -0.66
     scatt
    -0.64
     poichè
    -0.63
     Ciò
    -0.62
     incompet
    -0.62
    POSITIVE LOGITS
     Francisco
    1.13
    Francisco
    0.97
     SF
    0.90
     francisco
    0.82
     FRANCISCO
    0.81
    SF
    0.80
     Berkeley
    0.76
     sf
    0.71
     San
    0.69
    sf
    0.69
    Activations Density 0.070%

    No Known Activations