© 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. 774
    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%
    461
    +0.06
    0.2%
    555
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.07
    0.03
    1880
    +0.06
    0.03
    397
    +0.06
    0.03
    Negative Logits
    ⓧ
    -1.20
    <bos>
    -1.19
    <?
    -1.03
    
    
    -1.01
     shuddered
    -0.95
     shivered
    -0.88
    /**
    -0.86
     sobbed
    -0.84
     gratify
    -0.83
     overthrown
    -0.81
    POSITIVE LOGITS
     Press
    1.50
    Press
    1.27
     maroc
    1.09
     PRESS
    1.03
     marte
    0.96
     marea
    0.95
     Décembre
    0.92
     pép
    0.92
     pleins
    0.90
     Février
    0.89
    Activations Density 0.070%

    No Known Activations