© 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. 7727
    Prev
    Next
    INDEX
    Explanations

    specific sequences or descriptions related to a product or manual

    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
    +0.27
    1.4%
    1265
    +0.13
    0.7%
    2019
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.27
    0.06
    1173
    +0.13
    0.04
    1757
    +0.12
    0.05
    Negative Logits
    <bos>
    -3.03
    ⓧ
    -0.76
    /***
    -0.74
    <?
    -0.68
    <?
    -0.65
     disambigu
    -0.63
    //};
    -0.63
     localize
    -0.62
     springfox
    -0.60
    })();
    -0.59
    POSITIVE LOGITS
     quoque
    0.67
     conster
    0.62
     pylab
    0.62
     ejus
    0.60
     Púb
    0.60
    pylab
    0.60
     minY
    0.60
     cæ
    0.60
     jajaja
    0.59
     bienven
    0.58
    Activations Density 0.332%

    No Known Activations