© 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. 4889
    Prev
    Next
    INDEX
    Explanations

    conversations including questions, answers, explanations, and statements

    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
    +0.18
    0.7%
    1150
    +0.15
    0.6%
    453
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.18
    0.07
    817
    +0.15
    0.07
    399
    +0.11
    0.07
    Negative Logits
    <bos>
    -2.60
     intersper
    -1.08
    /***
    -0.96
    ⓧ
    -0.87
     defray
    -0.80
     endow
    -0.78
    /**
    -0.75
     encomp
    -0.75
     harmonize
    -0.72
     disbur
    -0.72
    POSITIVE LOGITS
    gruntled
    0.56
    :].
    0.56
    %";
    0.55
    cassert
    0.55
     imprescin
    0.54
     seksi
    0.52
    abancı
    0.52
     biblia
    0.52
     Doktor
    0.51
     conster
    0.51
    Activations Density 0.436%

    No Known Activations