© 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. 12188
    Prev
    Next
    INDEX
    Explanations

    information related to technical specifications and features of solar units or portable devices

    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
    1763
    +0.13
    0.6%
    680
    +0.13
    0.6%
    1059
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.13
    0.02
    538
    +0.13
    0.02
    1763
    +0.13
    0.02
    Negative Logits
     Muitos
    -0.80
     viciss
    -0.76
     Mesmo
    -0.75
     thermomix
    -0.74
     caprice
    -0.74
     Talvez
    -0.74
     unlaw
    -0.72
     indestru
    -0.69
     shenan
    -0.69
     volunte
    -0.67
    POSITIVE LOGITS
     Por
    1.45
    Por
    1.38
     por
    1.28
     POR
    1.27
    por
    1.25
    POR
    1.15
     Porter
    1.02
     PORT
    1.01
     porter
    0.95
    PORT
    0.93
    Activations Density 0.125%

    No Known Activations