© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2878
    Prev
    Next
    INDEX
    Explanations

    instances of characters indicating quotations or dialogue

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    871
    +0.10
    0.3%
    1047
    +0.09
    0.3%
    492
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.10
    0.02
    1201
    +0.09
    0.02
    1976
    +0.09
    0.02
    Negative Logits
    —
    -1.01
     —
    -0.83
    <bos>
    -0.71
    "—
    -0.69
    )—
    -0.60
     •
    -0.59
    ”—
    -0.58
    .—
    -0.57
    </h2>
    -0.56
     remain
    -0.56
    POSITIVE LOGITS
     `
    1.91
    `
    1.84
     (`
    1.64
    .`
    1.60
    )`
    1.57
    ]`
    1.49
    `.
    1.48
     `.
    1.46
    >`
    1.42
    (`
    1.40
    Activations Density 0.190%

    No Known Activations