© 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. 12456
    Prev
    Next
    INDEX
    Explanations

    names of movies, directors, and writers from film awards ceremonies

    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
    1577
    +0.29
    1.1%
    1842
    +0.26
    1.0%
    394
    +0.20
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.29
    0.04
    1842
    +0.26
    0.08
    163
    +0.20
    0.04
    Negative Logits
     encomp
    -0.81
     viciss
    -0.78
     munich
    -0.72
     Pyrene
    -0.70
     unve
    -0.70
    LookAnd
    -0.69
     Ecclesiastical
    -0.68
     Czechos
    -0.67
     Abbé
    -0.66
     unlaw
    -0.65
    POSITIVE LOGITS
     Politique
    0.49
     parceiros
    0.43
    FontFamily
    0.43
    Trichloroethane
    0.43
     lte
    0.41
     potes
    0.41
     MemoryStream
    0.41
     Leinwand
    0.41
    typeorm
    0.40
    macar
    0.40
    Activations Density 1.144%

    No Known Activations