© 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. 5664
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and law enforcement actions

    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
    805
    +0.15
    0.5%
    1778
    +0.14
    0.5%
    1464
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.15
    0.03
    805
    +0.14
    0.03
    1425
    +0.11
    0.02
    Negative Logits
     CURI
    -0.51
     reger
    -0.49
    livejournal
    -0.47
    jimmy
    -0.46
     truff
    -0.44
     besta
    -0.43
     verg
    -0.43
    Personendaten
    -0.42
     giz
    -0.42
    Diz
    -0.41
    POSITIVE LOGITS
     prosecutors
    1.16
    Prosecutors
    1.14
     Prosec
    1.09
     prosecutor
    1.07
     prosecution
    1.06
     prosecuting
    1.03
     prosecuted
    1.01
     Prosecution
    1.01
    Prosec
    1.00
     prosecute
    0.98
    Activations Density 0.078%

    No Known Activations