© 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. 7411
    Prev
    Next
    INDEX
    Explanations

    information related to health and finance, focusing on studies and expert opinions

    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
    674
    +0.10
    0.3%
    1714
    +0.07
    0.2%
    1618
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1368
    +0.10
    0.02
    1383
    +0.07
    0.03
    649
    +0.07
    0.03
    Negative Logits
     accla
    -0.92
     compen
    -0.89
     ivi
    -0.88
     Keny
    -0.87
     délib
    -0.86
    !!</
    -0.86
     ardu
    -0.86
     endom
    -0.86
     Manufact
    -0.85
     suspic
    -0.85
    POSITIVE LOGITS
     downright
    0.83
     entirely
    0.80
     altogether
    0.79
     completely
    0.78
     outright
    0.78
     nonexistent
    0.74
     totally
    0.74
    sightly
    0.71
     zero
    0.69
     complete
    0.67
    Activations Density 0.208%

    No Known Activations