© 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. 5434
    Prev
    Next
    INDEX
    Explanations

    contexts related to law, activism, and societal issues

    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
    1870
    +0.12
    0.4%
    1861
    +0.09
    0.3%
    1592
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.12
    0.04
    284
    +0.09
    0.07
    1380
    +0.08
    0.03
    Negative Logits
     emphat
    -2.23
     accla
    -2.05
     meis
    -2.05
     reluct
    -2.04
     pessi
    -2.01
     „,
    -1.97
     effe
    -1.96
     mef
    -1.95
     abnorm
    -1.92
     increa
    -1.92
    POSITIVE LOGITS
     throughout
    0.85
     across
    0.84
     from
    0.81
     of
    0.80
     between
    0.80
     within
    0.79
     and
    0.78
     through
    0.77
     towards
    0.76
     among
    0.76
    Activations Density 0.596%

    No Known Activations