© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4470
    Prev
    Next
    INDEX
    Explanations

    mentions of academic and partnership activities within specific universities

    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
    1499
    +0.21
    0.7%
    304
    +0.17
    0.6%
    939
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.21
    0.04
    678
    +0.17
    0.03
    1830
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.18
    ,
    -1.16
    .
    -1.12
    ↵
    -1.11
    ↵↵
    -1.11
     (
    -1.10
     
    -1.09
    ;
    -1.06
     and
    -1.05
     in
    -1.03
    POSITIVE LOGITS
     pessi
    2.86
     ritard
    2.56
     igno
    2.52
     suspic
    2.51
     pernic
    2.50
     marcato
    2.50
     emphat
    2.48
     trion
    2.48
     gend
    2.46
     embra
    2.45
    Activations Density 0.099%

    No Known Activations