© 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. 4429
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement activities, investigations, and legal proceedings

    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
    184
    +0.10
    0.3%
    882
    +0.10
    0.3%
    1150
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.10
    0.04
    464
    +0.10
    0.03
    1048
    +0.09
    0.01
    Negative Logits
     doveva
    -0.87
     meis
    -0.83
     blin
    -0.78
     parf
    -0.77
     imposs
    -0.76
     glan
    -0.76
     vort
    -0.76
     wien
    -0.76
     gioca
    -0.74
     anse
    -0.74
    POSITIVE LOGITS
     vedno
    0.59
     palju
    0.57
     väga
    0.55
    ajemy
    0.52
    PushMatrix
    0.51
     conformité
    0.51
     nekaj
    0.51
     déclarations
    0.51
     contenus
    0.51
    ioutil
    0.51
    Activations Density 0.221%

    No Known Activations