© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 7269
    Prev
    Next
    INDEX
    Explanations

    items related to measurements, specifications, or technical details, especially those involving dimensions such as length and width

    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
    +0.19
    1.1%
    538
    +0.14
    0.8%
    1810
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.19
    0.04
    538
    +0.14
    0.04
    1810
    +0.12
    0.03
    Negative Logits
    <bos>
    -3.11
    <?
    -1.13
    
    
    -1.06
    /**
    -1.04
    ⓧ
    -1.00
    /***
    
    -0.80
    <?
    
    -0.78
    /*
    -0.73
    ///**
    -0.72
    ItemBackground
    -0.65
    POSITIVE LOGITS
     véhic
    1.24
     délib
    1.20
     pleins
    1.10
     préc
    1.09
     quoique
    1.08
     soulign
    1.07
     considér
    1.05
     énorm
    1.04
     inconnu
    1.02
     quelquefois
    1.02
    Activations Density 0.054%

    No Known Activations