© 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. 178
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to art and sculpture

    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
    1810
    +0.08
    0.3%
    331
    +0.08
    0.2%
    177
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.03
    997
    +0.08
    0.02
    300
    +0.07
    0.02
    Negative Logits
    cshtml
    -0.69
    ParallelGroup
    -0.68
    Kích
    -0.67
    GroupLayout
    -0.66
    }{||
    -0.63
    /***/
    -0.62
    ValueGenerated
    -0.62
    Nguồn
    -0.60
    Ảnh
    -0.59
    WriteLiteral
    -0.59
    POSITIVE LOGITS
    ko
    2.55
     ftu
    2.09
     fte
    2.02
     guarante
    2.01
     reft
    2.00
     thut
    2.00
     fta
    1.99
     strick
    1.99
     increa
    1.99
     secon
    1.98
    Activations Density 0.158%

    No Known Activations