© 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. 7422
    Prev
    Next
    INDEX
    Explanations

    time durations specified as the number of months

    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
    +0.12
    0.4%
    1387
    +0.11
    0.4%
    501
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1983
    +0.12
    0.04
    703
    +0.11
    0.04
    147
    +0.11
    0.03
    Negative Logits
     Noviembre
    -0.70
     Luglio
    -0.70
     Diciembre
    -0.68
     parteci
    -0.68
     Ottobre
    -0.66
     Febrero
    -0.64
     Septiembre
    -0.63
    **********/
    -0.59
     Giugno
    -0.59
     apparti
    -0.58
    POSITIVE LOGITS
     months
    1.00
    months
    0.99
    Months
    0.91
     Months
    0.91
     MONTHS
    0.84
     month
    0.84
    month
    0.81
     Month
    0.77
     MONTH
    0.73
    Month
    0.71
    Activations Density 0.110%

    No Known Activations