© 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. 13223
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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
    +0.14
    0.4%
    1978
    +0.12
    0.4%
    1757
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.14
    0.05
    101
    +0.12
    0.04
    1343
    +0.12
    0.05
    Negative Logits
     tolerably
    -1.32
     gaily
    -1.30
     depic
    -1.25
     shenan
    -1.22
     reluct
    -1.21
     unspeak
    -1.20
     impractica
    -1.20
     intersper
    -1.20
     impra
    -1.16
     maneu
    -1.16
    POSITIVE LOGITS
    4
    0.94
     behar
    0.82
     parati
    0.79
     sement
    0.77
     erd
    0.76
    Ⅳ
    0.71
     pól
    0.70
     guz
    0.70
     lü
    0.70
     lomb
    0.69
    Activations Density 0.150%

    No Known Activations