© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6977
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How do you" or "How do I"

    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
    •Steering
    fun feature

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.9%
    1101
    +0.11
    0.5%
    484
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.20
    0.04
    1101
    +0.11
    0.05
    68
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.70
    ⓧ
    -0.91
    <?
    -0.84
    
    
    -0.72
    /***
    
    -0.71
    /**
    -0.69
    <?
    
    -0.59
    ///**
    -0.55
    Портали
    -0.54
    Kontrola
    -0.53
    POSITIVE LOGITS
     seksi
    1.14
     riva
    1.06
     signora
    1.04
     Karang
    1.02
     monaster
    1.01
     maksi
    1.00
     Muhamma
    1.00
     thuy
    0.98
     saar
    0.97
     keramik
    0.95
    Activations Density 0.401%

    No Known Activations