© 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 EvalsExportsinterp-engineNEWAPI 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. 15229
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers in various publication references

    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
    1343
    +0.21
    0.7%
    453
    +0.14
    0.4%
    2019
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.21
    0.03
    453
    +0.14
    0.03
    906
    +0.11
    0.00
    Negative Logits
     heapq
    -0.69
     împre
    -0.68
     smtplib
    -0.68
     concorso
    -0.64
     partecipa
    -0.63
     venit
    -0.62
     affitto
    -0.62
     začet
    -0.59
     archivio
    -0.58
     vacanza
    -0.58
    POSITIVE LOGITS
     CPO
    0.58
     MIM
    0.55
     AFS
    0.52
     GSC
    0.52
     CY
    0.52
     OCS
    0.52
    Modem
    0.51
     PTC
    0.51
     PDI
    0.51
     PMS
    0.51
    Activations Density 0.101%

    No Known Activations