© 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. 7407
    Prev
    Next
    INDEX
    Explanations

    comparisons of speed, size, and power

    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
    1013
    +0.07
    0.2%
    915
    +0.07
    0.2%
    792
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1100
    +0.07
    0.04
    1118
    +0.07
    0.04
    224
    +0.07
    0.04
    Negative Logits
     kram
    -1.06
     doman
    -1.01
     „,
    -0.98
     sena
    -0.92
     sement
    -0.92
     solidar
    -0.91
     mef
    -0.91
     sii
    -0.91
     lele
    -0.91
     kac
    -0.90
    POSITIVE LOGITS
     than
    1.17
     compared
    0.96
     decât
    0.93
    than
    0.86
    Than
    0.83
     kuin
    0.77
     niż
    0.74
     THAN
    0.73
    compared
    0.72
     Than
    0.69
    Activations Density 0.231%

    No Known Activations