© 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. 14719
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement and security measures in a community settings

    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
    +0.09
    0.3%
    2045
    +0.09
    0.3%
    1336
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2045
    +0.09
    0.06
    658
    +0.09
    0.06
    1336
    +0.09
    0.05
    Negative Logits
     rhum
    -0.56
     veu
    -0.55
     transfé
    -0.55
     tarte
    -0.55
     parma
    -0.54
     doman
    -0.54
     igno
    -0.54
     gouver
    -0.54
     vache
    -0.53
     xenia
    -0.52
    POSITIVE LOGITS
     stationed
    0.63
     tasked
    0.61
     trained
    0.59
     specializing
    0.56
     hired
    0.54
     felicity
    0.53
     fulness
    0.53
     dedicated
    0.52
     capable
    0.51
    bufio
    0.50
    Activations Density 0.510%

    No Known Activations