© 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. 4117
    Prev
    Next
    INDEX
    Explanations

    **data visualization elements or references to charts/graphs.**

    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
    1937
    +0.19
    0.7%
    1573
    +0.18
    0.7%
    1376
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.19
    0.03
    1937
    +0.18
    0.02
    1059
    +0.12
    0.02
    Negative Logits
     lü
    -0.67
     paille
    -0.62
     Paix
    -0.62
     izvē
    -0.60
     maske
    -0.59
     drap
    -0.59
     kram
    -0.57
     glan
    -0.57
     armen
    -0.56
     soigne
    -0.56
    POSITIVE LOGITS
     chart
    1.46
     charts
    1.34
    chart
    1.31
     Chart
    1.22
    Chart
    1.22
     Charts
    1.13
     CHART
    1.11
     charting
    1.10
    Charts
    1.02
    charts
    1.01
    Activations Density 0.055%

    No Known Activations