© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1006
    Prev
    Next
    INDEX
    Explanations

    key terms related to law enforcement, criminal activities like arson, arrests, and seizures

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1890
    +0.07
    0.2%
    2004
    +0.07
    0.2%
    812
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.02
    1363
    +0.07
    0.05
    1343
    +0.07
    0.06
    Negative Logits
    Și
    -0.71
     onAnimation
    -0.70
    ghijkl
    -0.63
     Și
    -0.61
    ategories
    -0.58
    áfrica
    -0.58
    URLException
    -0.58
    ilibrium
    -0.57
    ladiator
    -0.57
    UVWXYZ
    -0.57
    POSITIVE LOGITS
    ■
    1.99
     ■
    1.34
     encomp
    1.10
    ■■
    1.06
     stickied
    1.00
     shenan
    0.98
     depic
    0.94
     Pamphlet
    0.91
     intersper
    0.90
     apprehen
    0.89
    Activations Density 0.478%

    No Known Activations