© 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. 779
    Prev
    Next
    INDEX
    Explanations

    text related to criminal activities and law enforcement efforts

    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
    382
    +0.18
    0.6%
    1150
    +0.18
    0.6%
    1741
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.18
    0.07
    1445
    +0.18
    0.07
    1150
    +0.13
    0.04
    Negative Logits
     ordina
    -1.19
     affez
    -1.17
     lampa
    -1.16
     moza
    -1.16
     ananas
    -1.13
     torba
    -1.13
     maroc
    -1.12
     kask
    -1.12
     meis
    -1.11
     tuta
    -1.10
    POSITIVE LOGITS
     unspeak
    1.05
     whose
    0.96
     who
    0.86
     indescri
    0.80
     whom
    0.78
    whose
    0.76
     impelled
    0.75
     which
    0.73
     vainly
    0.71
     aka
    0.70
    Activations Density 0.301%

    No Known Activations