© 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. 0-RES-JB
    6. 792
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    50
    +0.07
    0.2%
    710
    +0.06
    0.2%
    175
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.07
    0.04
    725
    +0.06
    0.03
    1466
    +0.06
    0.03
    Negative Logits
     nawr
    -0.68
    initView
    -0.64
    /***
    
    -0.61
     насеља
    -0.60
    BUYER
    -0.60
    само
    -0.57
    Enllaços
    -0.57
    spesies
    -0.56
    ApiOperation
    -0.56
    <?
    
    -0.56
    POSITIVE LOGITS
     wien
    1.57
     chrysler
    1.47
     fei
    1.43
     aen
    1.42
     idr
    1.42
     fta
    1.41
     maneu
    1.40
     lele
    1.40
     mef
    1.39
     myn
    1.39
    Activations Density 0.217%

    No Known Activations