© 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. 3211
    Prev
    Next
    INDEX
    Explanations

    content related to information technology, blogging, and communication

    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
    +0.21
    0.8%
    766
    +0.10
    0.4%
    1224
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    766
    +0.21
    0.11
    1820
    +0.10
    0.08
    1799
    +0.07
    0.07
    Negative Logits
    <bos>
    -1.82
    
    -0.71
    <?
    -0.69
     AssemblyCompany
    -0.66
    lateinit
    -0.64
    ൊ
    -0.63
    ▼
    -0.63
     INSEE
    -0.62
    #
    -0.62
    //
    -0.62
    POSITIVE LOGITS
     impra
    1.91
     disreg
    1.91
     maneu
    1.89
     reluct
    1.82
     affor
    1.80
     accla
    1.75
     scrat
    1.72
     embodi
    1.72
     unlaw
    1.71
     depic
    1.71
    Activations Density 2.117%

    No Known Activations