© 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. 129
    Prev
    Next
    INDEX
    Explanations

    reviews describing quality or condition as 'excellent'

    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
    50
    +0.11
    0.5%
    478
    +0.07
    0.3%
    1823
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.11
    0.04
    1446
    +0.07
    0.04
    994
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.34
    
    -0.90
    <?
    -0.89
    ⓧ
    -0.82
    /**
    -0.80
    <?
    -0.78
    /*
    -0.73
    <!--
    -0.71
    /***
    -0.69
    migrationBuilder
    -0.63
    POSITIVE LOGITS
    excellent
    1.59
     excellent
    1.56
     EXCELL
    1.44
     Excellent
    1.42
    Excellent
    1.42
     Minang
    1.37
     bandung
    1.37
     maneu
    1.37
     jaya
    1.33
     stockholm
    1.33
    Activations Density 0.105%

    No Known Activations