© 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. 4093
    Prev
    Next
    INDEX
    Explanations

    references to a specific publication, the Wall Street Journal

    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
    1376
    +0.14
    0.5%
    1372
    +0.11
    0.4%
    597
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.14
    0.03
    1372
    +0.11
    0.02
    648
    +0.10
    0.02
    Negative Logits
     kokos
    -0.66
     keram
    -0.64
     hek
    -0.59
     kram
    -0.53
     kran
    -0.52
     frambo
    -0.51
     aimable
    -0.50
    leine
    -0.49
     wien
    -0.49
     krab
    -0.48
    POSITIVE LOGITS
     Street
    0.81
     Valentín
    0.73
     street
    0.73
     Darío
    0.70
     Mejía
    0.69
    Street
    0.69
     STREET
    0.68
     Marín
    0.68
    street
    0.64
     Domínguez
    0.64
    Activations Density 0.046%

    No Known Activations