© 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. 4531
    Prev
    Next
    INDEX
    Explanations

    information regarding sports players, their performance, and future prospects

    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
    1577
    +0.27
    1.0%
    50
    +0.19
    0.7%
    394
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.27
    0.25
    392
    +0.19
    0.08
    581
    +0.15
    0.14
    Negative Logits
     Ottobre
    -0.87
     Settembre
    -0.82
     affez
    -0.79
     CiNii
    -0.79
     Luglio
    -0.74
     sepol
    -0.73
     sentito
    -0.72
     Unito
    -0.70
     Giugno
    -0.70
     affari
    -0.70
    POSITIVE LOGITS
     sophistic
    1.03
     philanth
    0.99
     shenan
    0.99
     McLaugh
    0.94
     intrigu
    0.87
     pamph
    0.85
     ineffec
    0.85
     horrend
    0.83
     stickied
    0.83
     apprehen
    0.82
    Activations Density 7.137%

    No Known Activations