© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6599
    Prev
    Next
    INDEX
    Explanations

    positive and negative evaluations or opinions with a focus on emotions or reactions

    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
    0.8%
    689
    +0.10
    0.4%
    1839
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1839
    +0.19
    0.10
    446
    +0.10
    0.07
    1245
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.50
    ⓧ
    -0.97
    <?
    -0.78
    /**
    -0.75
    
    -0.74
    /*++
    -0.70
    <tfoot>
    -0.68
     inaugurate
    -0.66
     harmonize
    -0.65
     consolidate
    -0.62
    POSITIVE LOGITS
     meis
    1.03
     thuy
    1.00
     maroc
    0.94
     tyn
    0.94
     wien
    0.94
     kaos
    0.93
     haer
    0.93
    quarelle
    0.93
     fers
    0.93
     kark
    0.92
    Activations Density 1.042%

    No Known Activations