© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    mentions of marijuana legislation and related terms

    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
    1068
    +0.15
    0.6%
    1742
    +0.14
    0.6%
    1407
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.15
    0.03
    1622
    +0.14
    0.02
    314
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.77
    Đặc
    -0.69
    assertj
    -0.68
    reset
    -0.65
    BindView
    -0.65
    JTextArea
    -0.65
    LEADING
    -0.65
    get
    -0.65
    fore
    -0.61
    ToolStrip
    -0.61
    POSITIVE LOGITS
     maneu
    1.92
     disagre
    1.79
     shenan
    1.67
     reluct
    1.67
     apprehen
    1.64
     unspeak
    1.62
     Abbé
    1.61
     depic
    1.61
     gaily
    1.61
     stockholm
    1.61
    Activations Density 0.378%

    No Known Activations