© 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. 14856
    Prev
    Next
    INDEX
    Explanations

    mentions of physical removal or alteration in a social or political context

    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
    1392
    +0.12
    0.4%
    874
    +0.10
    0.3%
    61
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.12
    0.03
    1392
    +0.10
    0.04
    61
    +0.10
    0.03
    Negative Logits
     impractica
    -0.89
     reluct
    -0.86
     disagre
    -0.85
     affor
    -0.84
     impra
    -0.82
     perfet
    -0.81
     excru
    -0.81
     scrat
    -0.79
     uninten
    -0.79
     Wtf
    -0.78
    POSITIVE LOGITS
     removal
    1.06
     remove
    1.04
     removed
    1.02
    remove
    1.02
     removes
    1.00
    Remove
    0.98
     Remove
    0.97
     Removal
    0.94
    removed
    0.94
     removing
    0.90
    Activations Density 0.148%

    No Known Activations