© 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. 2749
    Prev
    Next
    INDEX
    Explanations

    references to police patrolmen and awards related to exceptional community service

    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
    1092
    +0.10
    0.3%
    991
    +0.10
    0.3%
    1137
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.10
    0.03
    925
    +0.10
    0.02
    991
    +0.07
    0.02
    Negative Logits
    writeObject
    -0.55
    setViewName
    -0.54
    setBold
    -0.53
     em
    -0.50
     Emb
    -0.50
     got
    -0.50
    mainAxisSize
    -0.50
    em
    -0.50
    CloseOperation
    -0.50
    })();
    -0.49
    POSITIVE LOGITS
     patrol
    2.63
     Patrol
    2.60
    patrol
    2.36
     patrols
    2.27
    Patrol
    2.25
     patrolling
    1.85
     ftu
    1.26
     emphat
    1.20
     effe
    1.17
     embodi
    1.14
    Activations Density 0.194%

    No Known Activations