© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6704
    Prev
    Next
    INDEX
    Explanations

    questions about identity and roles

    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
    +0.18
    0.9%
    1573
    +0.12
    0.6%
    1506
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.18
    0.05
    1194
    +0.12
    0.04
    1573
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.96
    <?
    -0.77
    ⓧ
    -0.75
    /***
    -0.69
    /**
    -0.60
     relieve
    -0.56
     adopt
    -0.54
     enrich
    -0.54
    
    -0.54
     infuse
    -0.54
    POSITIVE LOGITS
     Minang
    1.28
     quæ
    1.16
     bandung
    1.11
     marseille
    1.10
     Février
    1.10
     quoique
    1.09
     Karang
    1.07
     Khart
    1.06
     ados
    1.05
     Souha
    1.05
    Activations Density 0.235%

    No Known Activations