© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2739
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location, Chula Vista, along with related activities and groups from that area

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    1047
    +0.09
    0.3%
    204
    +0.07
    0.2%
    1392
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.03
    283
    +0.07
    0.01
    1972
    +0.07
    0.02
    Negative Logits
    etermined
    -0.67
    eniably
    -0.66
    oforms
    -0.64
     endnu
    -0.60
    itchfield
    -0.58
    Mesmo
    -0.58
    amaged
    -0.57
    Eksterne
    -0.56
     before
    -0.56
    Ainda
    -0.56
    POSITIVE LOGITS
    ula
    2.92
    ULA
    2.13
    ulas
    1.77
     inder
    1.29
     fuf
    1.28
    ulae
    1.25
     daz
    1.25
     effe
    1.22
     lidl
    1.20
     wien
    1.20
    Activations Density 0.200%

    No Known Activations