© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6848
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific villa

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    204
    +0.15
    0.8%
    1334
    +0.14
    0.7%
    597
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.15
    0.03
    1406
    +0.14
    0.02
    1334
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.25
    /**
    -0.70
    
    
    -0.68
     springfox
    -0.65
    ⓧ
    -0.62
    AutoScaleMode
    -0.58
    latego
    -0.56
    <?
    
    -0.55
    Сло
    -0.54
    ętr
    -0.53
    POSITIVE LOGITS
     Villa
    1.71
    Villa
    1.63
     villa
    1.57
     VILLA
    1.45
    villa
    1.33
     villas
    1.28
    VILLA
    1.27
     Villas
    1.23
     VILL
    1.15
     Vill
    1.04
    Activations Density 0.359%

    No Known Activations