© 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. 12344
    Prev
    Next
    INDEX
    Explanations

    specific details about architectural and infrastructural developments

    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
    478
    +0.22
    0.7%
    2034
    +0.14
    0.4%
    1224
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.22
    0.09
    1533
    +0.14
    0.05
    19
    +0.13
    0.06
    Negative Logits
    nasel
    -0.81
    wieś
    -0.80
    Terug
    -0.77
    Welke
    -0.77
    ⓧ
    -0.76
    Przyp
    -0.75
    Lindo
    -0.75
     pymysql
    -0.74
    źródło
    -0.74
    Kaip
    -0.74
    POSITIVE LOGITS
     adesi
    0.79
     allarg
    0.76
     paradiso
    0.76
     fers
    0.74
     siff
    0.74
    (%)
    0.72
     vasi
    0.72
     sopr
    0.71
     trasparente
    0.71
    peka
    0.71
    Activations Density 0.355%

    No Known Activations