© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 736
    Prev
    Next
    INDEX
    Explanations

    words ending in "ria."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    545
    +0.08
    0.2%
    1983
    +0.07
    0.2%
    1708
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.04
    283
    +0.07
    0.01
    143
    +0.07
    0.03
    Negative Logits
     kasarigan
    -0.69
    modb
    -0.68
     typelib
    -0.64
    脚注の使い方
    -0.64
    róleo
    -0.64
     سكانية
    -0.64
    namefont
    -0.64
    HasAnnotation
    -0.62
    ecore
    -0.62
    ParallelGroup
    -0.62
    POSITIVE LOGITS
    ria
    1.90
     increa
    1.85
     affor
    1.72
     scrat
    1.65
     indestru
    1.62
     guarante
    1.62
    rian
    1.61
     maneu
    1.60
     depic
    1.60
     hairc
    1.58
    Activations Density 0.246%

    No Known Activations