© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4122
    Prev
    Next
    INDEX
    Explanations

    technical details and product features in descriptions

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1137
    +0.15
    0.8%
    406
    +0.14
    0.8%
    596
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.05
    1741
    +0.14
    -0.00
    478
    +0.13
    0.02
    Negative Logits
    <bos>
    -0.84
    danke
    -0.65
    
    -0.64
     segurando
    -0.62
    Contras
    -0.59
    Lato
    -0.57
     olhando
    -0.56
     oferec
    -0.56
    aspectj
    -0.56
    assertj
    -0.56
    POSITIVE LOGITS
     hood
    1.30
     Hood
    1.23
    Hood
    1.13
     hoods
    1.11
    HOOD
    0.95
    hood
    0.87
     toscana
    0.86
     palio
    0.81
     Jerusal
    0.81
     fuo
    0.80
    Activations Density 0.654%

    No Known Activations