© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2747
    Prev
    Next
    INDEX
    Explanations

    words related to cryptography and technical terms like "propeller," "lift," "drag," "biomimetics," and "aerodynamics."

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    204
    +0.10
    0.3%
    966
    +0.09
    0.3%
    286
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.10
    0.02
    204
    +0.09
    0.02
    1343
    +0.08
    0.03
    Negative Logits
     jenem
    -0.67
    ]-\
    -0.59
     jenen
    -0.58
     Niemand
    -0.58
    ]^{-
    -0.56
     reclaim
    -0.56
     synes
    -0.56
    displayquote
    -0.55
     dumbass
    -0.55
     manchen
    -0.55
    POSITIVE LOGITS
    der
    2.64
     Der
    2.22
    Der
    2.15
    DER
    2.09
     DER
    1.95
     der
    1.94
    ders
    1.51
    deri
    1.36
     deri
    1.35
    derr
    1.24
    Activations Density 0.176%

    No Known Activations