© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4097
    Prev
    Next
    INDEX
    Explanations

    phrases related to political law and justice, particularly highlighting the implications of accountability and the principles of justice

    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
    674
    +0.13
    0.4%
    1967
    +0.12
    0.3%
    1919
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.13
    0.07
    862
    +0.12
    0.04
    1377
    +0.08
    0.04
    Negative Logits
     apprehen
    -1.72
     disagre
    -1.64
     encomp
    -1.63
     increa
    -1.59
     depic
    -1.55
     reluct
    -1.55
     guarante
    -1.53
     unspeak
    -1.52
     gaily
    -1.50
     inev
    -1.45
    POSITIVE LOGITS
    <bos>
    0.89
     insuffisamment
    0.67
     resourceCulture
    0.60
    INSEE
    0.55
    xase
    0.53
     NSCoder
    0.52
    ğraf
    0.52
    ceis
    0.51
     Catawiki
    0.51
    WEBPACK
    0.50
    Activations Density 0.321%

    No Known Activations