© 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. 6-RES-JB
    11. 3826
    Prev
    Next
    INDEX
    Explanations

    technology specifications and features, including technical details about cameras, memory, and connectivity options for electronic devices

    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
    +0.27
    1.2%
    1842
    +0.14
    0.6%
    876
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.27
    0.14
    1403
    +0.14
    0.06
    924
    +0.12
    0.13
    Negative Logits
    <bos>
    -3.82
    ⓧ
    -1.08
    /***
    -0.96
    /**
    -0.94
    
    -0.88
    <?
    -0.86
     conferir
    -0.76
    /*
    -0.75
    lateinit
    -0.73
     aceitar
    -0.71
    POSITIVE LOGITS
     bandung
    1.22
     milano
    1.19
     jawa
    1.08
     lele
    1.07
     maroc
    1.07
     barcelona
    1.04
     santiago
    1.02
     riva
    1.02
     valencia
    1.00
     siena
    0.99
    Activations Density 2.468%

    No Known Activations