© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    the names of specific chemical compounds and plant species

    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
    +0.17
    0.7%
    227
    +0.12
    0.5%
    1499
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.05
    283
    +0.12
    0.01
    1405
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.72
    ⓧ
    -1.13
    <?
    -0.84
    
    -0.83
    /**
    -0.80
    /*
    -0.72
    Autoritní
    -0.64
     nahilalakip
    -0.64
    fektions
    -0.63
     يتيمه
    -0.61
    POSITIVE LOGITS
     Kategor
    1.09
     fameux
    1.08
     vété
    1.07
     |]
    1.06
     affor
    1.06
     increa
    1.01
     unden
    1.00
     applau
    0.99
     vry
    0.99
     strick
    0.98
    Activations Density 0.125%

    No Known Activations