© 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. 14397
    Prev
    Next
    INDEX
    Explanations

    locations and political entities mentioned in the text

    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
    2034
    +0.15
    0.4%
    1013
    +0.13
    0.4%
    50
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.15
    0.09
    227
    +0.13
    0.10
    1013
    +0.10
    0.09
    Negative Logits
     interessa
    -0.78
     aspetta
    -0.75
     vogliono
    -0.73
    Pued
    -0.73
     conosce
    -0.70
     apparti
    -0.63
     rendono
    -0.63
     adoro
    -0.61
     stiamo
    -0.60
     dicono
    -0.59
    POSITIVE LOGITS
     maneu
    1.13
     disagre
    1.08
     unspeak
    1.03
     snoopy
    1.00
     shenan
    0.99
     stickied
    0.97
     horrend
    0.96
     erad
    0.94
     cuck
    0.94
     disreg
    0.94
    Activations Density 0.689%

    No Known Activations