© 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. 14381
    Prev
    Next
    INDEX
    Explanations

    instances of numbers and numerical comparisons

    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
    488
    +0.08
    0.2%
    297
    +0.08
    0.2%
    1485
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.08
    0.05
    6
    +0.08
    0.04
    48
    +0.07
    0.04
    Negative Logits
     débats
    -0.48
    earcher
    -0.46
    agliari
    -0.45
     sourire
    -0.44
     malheur
    -0.43
    tigny
    -0.42
    upported
    -0.42
     larmes
    -0.41
     Imre
    -0.41
     inutile
    -0.40
    POSITIVE LOGITS
    :
    0.62
    :
    0.59
    DockStyle
    0.55
    ː
    0.54
    :\\
    0.53
    routeProvider
    0.53
     initComponents
    0.52
    awsze
    0.52
    CROSSTALK
    0.52
    $:
    0.52
    Activations Density 0.213%

    No Known Activations