© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1782
    Prev
    Next
    INDEX
    Explanations

    descriptions of significant size or scale, such as "massive" objects or deals

    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
    478
    +0.20
    1.1%
    1023
    +0.16
    0.9%
    871
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.20
    0.04
    517
    +0.16
    0.03
    1385
    +0.14
    0.04
    Negative Logits
    <bos>
    -2.48
    rungsseite
    -0.73
    OGND
    -0.71
    AsUp
    -0.70
    //};
    -0.70
    //});
    -0.70
    <?
    -0.70
    ResumeLayout
    -0.67
    displayquote
    -0.67
    //</
    -0.66
    POSITIVE LOGITS
     gabri
    1.63
     wien
    1.57
     stockholm
    1.55
     thut
    1.55
     yves
    1.54
     sergio
    1.53
     Juf
    1.53
     leonardo
    1.51
     napoli
    1.50
     ftu
    1.49
    Activations Density 0.363%

    No Known Activations