© 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. 2658
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal decrees or official orders

    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
    1023
    +0.08
    0.2%
    1823
    +0.07
    0.2%
    1950
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.08
    0.04
    1343
    +0.07
    0.04
    1120
    +0.07
    0.04
    Negative Logits
    Desen
    -0.81
     допо
    -0.68
    DataMember
    -0.67
    writeInt
    -0.67
     завжди
    -0.67
    bairro
    -0.67
    <0xF0>
    -0.66
    se
    -0.64
     per
    -0.64
    makedirs
    -0.63
    POSITIVE LOGITS
     fta
    2.07
     strick
    2.06
     reluct
    2.04
     increa
    2.02
     mef
    2.01
     depic
    2.01
     aen
    2.01
     stockholm
    2.00
     fte
    1.99
     emphat
    1.97
    Activations Density 0.311%

    No Known Activations