© 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. 2869
    Prev
    Next
    INDEX
    Explanations

    names, probably focusing on specific last names

    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
    1909
    +0.10
    0.3%
    896
    +0.08
    0.2%
    1276
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.02
    1508
    +0.08
    0.02
    488
    +0.07
    0.02
    Negative Logits
     gøre
    -0.80
     holde
    -0.73
     betale
    -0.68
     prøve
    -0.65
     sikre
    -0.65
     gjøre
    -0.64
     høre
    -0.62
     bruge
    -0.58
    <bos>
    -0.58
     skrive
    -0.58
    POSITIVE LOGITS
    vin
    2.69
    VIN
    1.90
     vin
    1.79
    Vin
    1.77
     Vin
    1.76
     VIN
    1.49
    vins
    1.34
    vina
    1.02
     Juf
    1.02
     |]
    1.01
    Activations Density 0.142%

    No Known Activations