© 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. 14826
    Prev
    Next
    INDEX
    Explanations

    terms related to security measures and potential vulnerabilities

    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
    1908
    +0.08
    0.2%
    1511
    +0.08
    0.2%
    391
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.08
    0.03
    208
    +0.08
    0.04
    1908
    +0.07
    0.03
    Negative Logits
     apprehen
    -1.78
     disagre
    -1.58
     reluct
    -1.54
     accla
    -1.47
     Juf
    -1.45
     unspeak
    -1.44
     shenan
    -1.42
     increa
    -1.41
     encomp
    -1.41
     reconno
    -1.39
    POSITIVE LOGITS
     lujo
    0.65
     afford
    0.62
     anymore
    0.62
    AnimationsModule
    0.56
     luxury
    0.55
     LIABLE
    0.54
    HideFlags
    0.54
     ménages
    0.52
     lose
    0.51
     darf
    0.51
    Activations Density 0.191%

    No Known Activations