© 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. 6370
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and consequences

    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
    +0.25
    1.2%
    1381
    +0.09
    0.4%
    1993
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1993
    +0.25
    0.04
    1751
    +0.09
    0.04
    1381
    +0.08
    0.04
    Negative Logits
    <bos>
    -3.64
    public
    -0.75
    andaag
    -0.69
    /*
    -0.64
    @
    -0.64
    //
    -0.64
    <eos>
    -0.63
    /**
    -0.63
    .
    -0.59
    ↵↵
    -0.59
    POSITIVE LOGITS
     stockholm
    1.53
     Minang
    1.44
     maroc
    1.44
     desir
    1.42
     lidl
    1.42
     wien
    1.41
     sovere
    1.41
     aen
    1.40
     applau
    1.39
     lyon
    1.38
    Activations Density 0.580%

    No Known Activations