© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1946
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Oakland and related entities

    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
    303
    +0.17
    0.7%
    1984
    +0.14
    0.6%
    1757
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.17
    0.03
    172
    +0.14
    0.02
    1984
    +0.13
    0.03
    Negative Logits
     Stowe
    -0.53
    спубли
    -0.51
    PerformLayout
    -0.50
    FTFY
    -0.50
     Litchfield
    -0.49
     unlaw
    -0.49
    Pue
    -0.48
     Kild
    -0.48
    Ikr
    -0.47
     Roswell
    -0.47
    POSITIVE LOGITS
     Oakland
    1.42
    Oakland
    1.27
     Berkeley
    0.85
    Berkeley
    0.77
     Alameda
    0.75
     Kalifor
    0.71
    OAK
    0.70
     OAK
    0.70
     Raiders
    0.67
     californ
    0.65
    Activations Density 0.110%

    No Known Activations