© 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. 779
    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
    568
    +0.09
    0.3%
    481
    +0.09
    0.3%
    144
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.09
    0.03
    568
    +0.09
    0.03
    1343
    +0.08
    0.03
    Negative Logits
    paddingVertical
    -0.65
    citenamefont
    -0.63
    postDelayed
    -0.61
    marginHorizontal
    -0.60
    SequentialGroup
    -0.56
    телна
    -0.56
     zumal
    -0.55
    ectady
    -0.55
     التش
    -0.54
    ToListAsync
    -0.54
    POSITIVE LOGITS
     Wo
    2.13
    Wo
    1.92
     Woo
    1.76
     WO
    1.76
     wo
    1.64
    Woo
    1.63
    WO
    1.62
    wo
    1.50
     Wool
    1.48
    Wool
    1.46
    Activations Density 0.225%

    No Known Activations