© 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. 2619
    Prev
    Next
    INDEX
    Explanations

    names of people or organizations

    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
    1335
    +0.09
    0.3%
    1979
    +0.08
    0.2%
    1480
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.06
    283
    +0.08
    0.02
    1363
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.00
     "..\..\
    -0.65
    ValueGenerated
    -0.59
    ⓧ
    -0.58
    Aholisi
    -0.56
     Voigt
    -0.54
     "..\..\..\
    -0.54
     potreb
    -0.53
     Offisielt
    -0.53
     Diener
    -0.50
    POSITIVE LOGITS
    err
    1.23
    raz
    1.22
     Ottobre
    0.92
     Settembre
    0.88
     err
    0.87
    ras
    0.86
     Giugno
    0.85
    ERR
    0.83
     Novembre
    0.82
     majest
    0.82
    Activations Density 0.314%

    No Known Activations