© 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. 2603
    Prev
    Next
    INDEX
    Explanations

    headlines or titles of various news stories

    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.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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1124
    +0.10
    0.3%
    1573
    +0.07
    0.2%
    645
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.10
    0.01
    1120
    +0.07
    0.05
    690
    +0.07
    0.05
    Negative Logits
    <bos>
    -0.97
     świad
    -0.75
     каса
    -0.66
    שמי
    -0.65
    нє
    -0.64
     уме
    -0.63
    рного
    -0.63
    فح
    -0.62
    ・
    -0.62
    里
    -0.62
    POSITIVE LOGITS
     meis
    2.02
     franz
    1.97
     oner
    1.85
     wien
    1.80
     afo
    1.77
     myn
    1.77
     alkoh
    1.74
     Kategor
    1.73
     carc
    1.72
     inder
    1.71
    Activations Density 0.344%

    No Known Activations