© 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. 4354
    Prev
    Next
    INDEX
    Explanations

    requests for help regarding criminal incidents

    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
    946
    +0.12
    0.3%
    453
    +0.09
    0.3%
    1696
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.12
    0.03
    1696
    +0.09
    0.02
    792
    +0.07
    0.02
    Negative Logits
     rempla
    -0.53
    throwable
    -0.51
     malheureux
    -0.51
    cityId
    -0.50
     négoci
    -0.49
    categoryName
    -0.48
     automne
    -0.48
    birthDate
    -0.47
     carbonic
    -0.47
     clayey
    -0.47
    POSITIVE LOGITS
     anyone
    0.61
    anyone
    0.59
     anybody
    0.57
     Anyone
    0.56
    Anyone
    0.54
    Anybody
    0.52
     ANYONE
    0.50
     Anybody
    0.49
     whereabouts
    0.49
    NOWLED
    0.48
    Activations Density 0.117%

    No Known Activations