© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4090
    Prev
    Next
    INDEX
    Explanations

    percentages and geographical terms related to revenue statistics

    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
    +0.27
    0.8%
    674
    +0.11
    0.3%
    381
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.27
    0.04
    609
    +0.11
    0.03
    1678
    +0.11
    0.03
    Negative Logits
     gaily
    -1.13
     McLaugh
    -0.94
     McInt
    -0.93
     sculptured
    -0.88
     Daven
    -0.88
     homeward
    -0.86
     nobly
    -0.84
     schoolmaster
    -0.83
     pamph
    -0.82
     avenger
    -0.80
    POSITIVE LOGITS
     apparti
    1.09
     sappi
    0.95
     assiste
    0.92
     perche
    0.88
     poichè
    0.87
     Ottobre
    0.87
     ordina
    0.86
     corris
    0.85
     purtroppo
    0.83
     dipende
    0.82
    Activations Density 0.090%

    No Known Activations