© 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. 213
    Prev
    Next
    INDEX
    Explanations

    names or mentions of specific locations (particularly Basel and Bern)

    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
    47
    +0.10
    0.3%
    313
    +0.09
    0.3%
    1276
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.05
    1343
    +0.09
    0.05
    690
    +0.09
    0.04
    Negative Logits
     intersper
    -1.60
     encomp
    -1.56
     🤣🤣
    -1.55
     hairc
    -1.55
     hentai
    -1.49
     lmfao
    -1.49
     milf
    -1.47
     increa
    -1.44
     stickied
    -1.40
     Lmao
    -1.39
    POSITIVE LOGITS
     Bern
    1.68
     Teb
    1.56
    Bern
    1.43
    Teb
    1.17
     Cer
    1.04
    Cer
    0.95
     quo
    0.85
     cer
    0.83
     BERN
    0.81
     Newtown
    0.80
    Activations Density 0.287%

    No Known Activations