© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11608
    Prev
    Next
    INDEX
    Explanations

    references to legal and political issues, including human rights violations, legal disputes, and policy debates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    2019
    +0.13
    0.4%
    390
    +0.11
    0.4%
    1108
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.13
    0.07
    390
    +0.11
    0.07
    1892
    +0.11
    0.06
    Negative Logits
     marte
    -1.00
     quoique
    -0.96
     applau
    -0.95
     LIRE
    -0.89
     aussitôt
    -0.85
     tricot
    -0.84
     Février
    -0.84
     pican
    -0.83
     canel
    -0.83
     artig
    -0.83
    POSITIVE LOGITS
     consequently
    0.80
     therefore
    0.78
     hence
    0.77
     thus
    0.77
     furthermore
    0.76
     thereby
    0.75
     also
    0.72
     then
    0.68
     moreover
    0.68
     subsequently
    0.67
    Activations Density 0.373%

    No Known Activations