© 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. 7757
    Prev
    Next
    INDEX
    Explanations

    event details, such as location, time, and cost

    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
    +0.20
    0.8%
    1618
    +0.10
    0.4%
    663
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.20
    0.15
    856
    +0.10
    0.08
    1499
    +0.10
    0.13
    Negative Logits
    <bos>
    -1.81
     intersper
    -1.51
     quitted
    -1.26
     encomp
    -1.19
     endeavoured
    -1.16
     shenan
    -1.14
     polaroid
    -1.08
     disbur
    -1.07
     endeavouring
    -1.06
     pamph
    -1.02
    POSITIVE LOGITS
    allclose
    0.77
    dropna
    0.72
     comté
    0.68
     Rektor
    0.66
     Sardegna
    0.65
     kalori
    0.64
    ChromeDriver
    0.64
    Trayectoria
    0.63
     kompati
    0.63
    : 
    0.63
    Activations Density 4.194%

    No Known Activations