© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2948
    Prev
    Next
    INDEX
    Explanations

    keywords related to protocols, procedures, and rules in technical contexts

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    437
    +0.08
    0.3%
    1961
    +0.08
    0.3%
    658
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.08
    0.02
    1430
    +0.08
    0.02
    658
    +0.08
    0.02
    Negative Logits
    <bos>
    -1.00
     răng
    -0.52
     pardoned
    -0.50
     spent
    -0.49
     spend
    -0.47
     engage
    -0.47
     spends
    -0.47
    ⓧ
    -0.47
     اله
    -0.47
     again
    -0.46
    POSITIVE LOGITS
     protocol
    2.86
     Protocol
    2.75
     Protocols
    2.58
     protocols
    2.57
    protocol
    2.49
    Protocol
    2.43
     PROTOCOL
    2.17
    protocols
    2.09
    Protocols
    2.08
     protocole
    2.02
    Activations Density 0.194%

    No Known Activations