© 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. 887
    Prev
    Next
    INDEX
    Explanations

    locations or events related to a specific place named Keeseville

    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
    871
    +0.09
    0.3%
    168
    +0.09
    0.3%
    795
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.03
    1101
    +0.09
    0.02
    168
    +0.09
    0.02
    Negative Logits
    <bos>
    -0.87
    public
    -0.76
    ด้วย
    -0.73
    -0.73
    多
    -0.73
     من
    -0.70
    ,
    -0.70
    export
    -0.69
     enable
    -0.69
    .
    -0.69
    POSITIVE LOGITS
     Ke
    2.52
     accla
    2.39
     increa
    2.24
    Ke
    2.21
     fuf
    2.19
     affor
    2.14
     depic
    2.12
     reluct
    2.10
     impra
    2.10
     suscep
    2.09
    Activations Density 0.147%
    No Known Activations