© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1877
    Prev
    Next
    INDEX
    Explanations

    positive descriptions or opinions

    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
    1777
    +0.08
    0.2%
    889
    +0.08
    0.2%
    1896
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.08
    0.02
    1876
    +0.08
    0.02
    889
    +0.08
    0.02
    Negative Logits
    
    -0.91
    <?
    -0.74
     quitted
    -0.65
    /**
    -0.64
    /*
    -0.62
     scrat
    -0.62
    <bos>
    -0.62
     excru
    -0.58
    SourceChecksum
    -0.58
     imposs
    -0.58
    POSITIVE LOGITS
     favorable
    2.17
     favourable
    2.13
     unfavorable
    1.80
     unfavourable
    1.75
     adverse
    1.69
    favorable
    1.66
     hostile
    1.47
    favourable
    1.44
     favorably
    1.43
     favorables
    1.35
    Activations Density 0.213%

    No Known Activations