© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scholarly articles and research publications, particularly focusing on issues such as effectiveness, health appraisal, environmental influences, and molecular biology

    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
    +0.46
    2.4%
    2019
    +0.14
    0.7%
    2034
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.46
    0.28
    1819
    +0.14
    0.18
    1213
    +0.08
    0.22
    Negative Logits
    public
    -0.70
    ਿੱ
    -0.69
    //
    -0.67
    ૌ
    -0.64
    ///
    -0.64
    <eos>
    -0.64
    起
    -0.64
    </tbody>
    -0.63
    /**
    -0.62
    /*
    -0.62
    POSITIVE LOGITS
     maneu
    2.03
     accla
    1.93
     affor
    1.84
     practition
    1.72
     erad
    1.71
     inev
    1.70
     impra
    1.70
     emphat
    1.66
     increa
    1.64
     excru
    1.63
    Activations Density 13.489%

    No Known Activations