© 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. 2794
    Prev
    Next
    INDEX
    Explanations

    phrase emphasizing completion or achievement

    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
    +0.16
    0.9%
    1472
    +0.15
    0.9%
    241
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1472
    +0.16
    0.10
    1994
    +0.15
    0.09
    1416
    +0.13
    0.08
    Negative Logits
    <bos>
    -3.15
    ⓧ
    -1.14
    /***
    -0.95
    
    -0.86
    <?
    -0.82
    /**
    -0.72
    <?
    -0.71
    Vegeu
    -0.68
     endow
    -0.68
     intersper
    -0.64
    POSITIVE LOGITS
     maroc
    1.07
     JUST
    0.95
    JUST
    0.94
    Just
    0.91
     ados
    0.89
     Just
    0.89
    just
    0.88
     riva
    0.87
     just
    0.87
     peugeot
    0.86
    Activations Density 0.178%

    No Known Activations