© 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. 2847
    Prev
    Next
    INDEX
    Explanations

    specific country names, particularly the Dominican Republic, mentioned in a news context

    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
    50
    +0.11
    0.4%
    776
    +0.05
    0.2%
    276
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1288
    +0.11
    0.09
    491
    +0.05
    0.07
    191
    +0.05
    0.05
    Negative Logits
    <bos>
    -1.84
     defaultstate
    -0.84
    addPreferredGap
    -0.83
    ⓧ
    -0.82
    glBind
    -0.82
    setClass
    -0.80
    ɵɵ
    -0.76
    glBindBuffer
    -0.76
    thâu
    -0.72
    Descripció
    -0.71
    POSITIVE LOGITS
     maneu
    2.18
     affor
    2.05
     increa
    2.03
     disagre
    2.00
     stockholm
    2.00
     lele
    2.00
     guarante
    1.98
     Juf
    1.98
     impra
    1.95
     apprehen
    1.94
    Activations Density 0.693%

    No Known Activations