© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1126
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions for a recipe

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.3%
    381
    +0.11
    0.5%
    1013
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1284
    +0.29
    0.09
    93
    +0.11
    0.08
    865
    +0.10
    0.08
    Negative Logits
    <bos>
    -2.08
    ⓧ
    -1.00
    /***
    -0.94
    ///**
    -0.83
    /**
    -0.74
     intersper
    -0.73
     disarm
    -0.71
    
    -0.69
     perpetuate
    -0.68
     enshr
    -0.67
    POSITIVE LOGITS
     soulign
    0.89
     contextLoads
    0.82
     catég
    0.81
     récentes
    0.81
     téléph
    0.77
     récents
    0.76
     LoginForm
    0.76
     évalu
    0.75
     originaux
    0.75
     pleins
    0.75
    Activations Density 0.314%

    No Known Activations