© 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. 7225
    Prev
    Next
    INDEX
    Explanations

    references to statistics, trends, and explanations

    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
    184
    +0.18
    0.5%
    1253
    +0.12
    0.4%
    1499
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.18
    0.02
    919
    +0.12
    0.02
    1499
    +0.10
    0.05
    Negative Logits
     disreg
    -0.94
     inappro
    -0.87
     unve
    -0.85
     suscep
    -0.85
     impra
    -0.84
     Docteur
    -0.84
     vété
    -0.83
     maneu
    -0.83
     viciss
    -0.83
     Mlle
    -0.82
    POSITIVE LOGITS
     increase
    0.63
    nocześnie
    0.63
     increases
    0.60
     decrease
    0.59
    xodo
    0.56
     guangdong
    0.56
    ोंने
    0.55
    ensement
    0.55
     decreases
    0.55
     hias
    0.52
    Activations Density 0.337%

    No Known Activations