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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13752
    Prev
    Next
    INDEX
    Explanations

    mentions of crimes and justice-related scenarios

    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
    2034
    +0.11
    0.3%
    1842
    +0.09
    0.3%
    1042
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.11
    0.04
    490
    +0.09
    0.03
    1882
    +0.09
    0.05
    Negative Logits
     dises
    -1.16
     grati
    -1.10
     sappi
    -1.09
     magis
    -1.06
     sopr
    -1.04
     igno
    -1.04
     sii
    -1.00
     dissi
    -0.99
     Chá
    -0.99
     illi
    -0.98
    POSITIVE LOGITS
     then
    0.77
     whether
    0.74
     chances
    0.73
     unless
    0.70
     if
    0.69
    whether
    0.68
     you
    0.68
     suddenly
    0.66
    then
    0.65
     Then
    0.65
    Activations Density 0.408%

    No Known Activations