© 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. 7421
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical concepts and news articles

    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
    752
    +0.17
    0.6%
    31
    +0.16
    0.6%
    1828
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1828
    +0.17
    0.08
    31
    +0.16
    0.07
    752
    +0.16
    0.06
    Negative Logits
     Pourtant
    -0.81
     Jusqu
    -0.79
     Leurs
    -0.71
     Maintenant
    -0.70
     Même
    -0.69
     Toutefois
    -0.67
     Plusieurs
    -0.64
     Ceux
    -0.62
     Malgré
    -0.60
     Beaucoup
    -0.58
    POSITIVE LOGITS
     ON
    0.81
     On
    0.72
     on
    0.67
     chantier
    0.62
     behalf
    0.60
    On
    0.59
     panneau
    0.59
     récomp
    0.58
     sentier
    0.55
     récon
    0.54
    Activations Density 0.309%

    No Known Activations