© 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. 0-RES-JB
    11. 1320
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms, potentially related to movies or characters

    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
    866
    +0.09
    0.2%
    325
    +0.08
    0.2%
    663
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.09
    0.05
    1343
    +0.08
    0.05
    283
    +0.08
    0.01
    Negative Logits
    relenting
    -0.72
     habang
    -0.72
     ļ
    -0.70
     itong
    -0.66
     חיצוניים
    -0.65
     Punj
    -0.62
    asteroide
    -0.62
     tamen
    -0.61
    Nuorodos
    -0.60
    Šaltiniai
    -0.60
    POSITIVE LOGITS
     mortal
    1.26
     mortals
    0.98
    mortal
    0.95
     immortal
    0.95
     Mortal
    0.94
     Fitzpatrick
    0.90
    onal
    0.89
    immortal
    0.87
    Fitz
    0.81
     Fitz
    0.81
    Activations Density 0.351%

    No Known Activations