© 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. 8066
    Prev
    Next
    INDEX
    Explanations

    references to the concept of potential and possibilities

    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
    50
    +0.20
    1.1%
    1671
    +0.09
    0.5%
    331
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1793
    +0.20
    0.03
    1512
    +0.09
    0.03
    1856
    +0.08
    0.03
    Negative Logits
    <bos>
    -3.44
    /*!
    -0.75
    Kontrola
    -0.70
    EndProject
    -0.67
    public
    -0.63
     maintain
    -0.62
    andaag
    -0.62
    <?
    -0.61
    Література
    -0.61
    enumerate
    -0.61
    POSITIVE LOGITS
     fta
    1.81
     stockholm
    1.74
     wien
    1.71
     squa
    1.69
     affor
    1.69
     thut
    1.68
     perfet
    1.68
     ftu
    1.66
     fte
    1.66
     tew
    1.63
    Activations Density 0.120%

    No Known Activations