© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and business

    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
    1177
    +0.13
    0.5%
    50
    +0.13
    0.5%
    678
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.13
    0.02
    678
    +0.13
    0.13
    1097
    +0.12
    0.12
    Negative Logits
    <bos>
    -2.13
    ⓧ
    -1.08
    intios
    -0.95
    CodeAttribute
    -0.87
     Paglinawan
    -0.87
    DeleteMapping
    -0.85
    tonode
    -0.83
    opsida
    -0.81
     NSCoder
    -0.80
    citenamefont
    -0.80
    POSITIVE LOGITS
     maneu
    2.04
     accla
    1.96
     shenan
    1.91
     resear
    1.90
     practition
    1.85
     reluct
    1.85
     affor
    1.85
     depic
    1.83
     inev
    1.80
     disagre
    1.79
    Activations Density 1.396%

    No Known Activations