© 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. 12465
    Prev
    Next
    INDEX
    Explanations

    information related to current events, news, or political affairs

    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
    1937
    +0.16
    0.5%
    478
    +0.14
    0.5%
    382
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.16
    0.11
    82
    +0.14
    0.07
    478
    +0.13
    0.06
    Negative Logits
     viendra
    -1.06
     susun
    -1.05
     bandung
    -1.03
     dépasse
    -1.02
     appartiennent
    -0.98
     remonte
    -0.98
     venuto
    -0.97
     tomba
    -0.94
     pousse
    -0.93
     sarili
    -0.92
    POSITIVE LOGITS
     currently
    1.03
     presently
    0.86
     now
    0.85
     reportedly
    0.81
     still
    0.80
    currently
    0.78
     likely
    0.76
     slated
    0.73
     supposed
    0.72
     considered
    0.72
    Activations Density 0.457%

    No Known Activations