© 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. 1621
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific product, promotional language, and vibrant descriptions

    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
    68
    +0.10
    0.3%
    1140
    +0.09
    0.3%
    893
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.04
    724
    +0.09
    0.03
    1927
    +0.08
    0.03
    Negative Logits
     mitte
    -0.76
     nõ
    -0.75
     väga
    -0.69
     jät
    -0.68
    WriteAttribute
    -0.65
     võimal
    -0.65
     front
    -0.65
     inimes
    -0.64
     nagu
    -0.63
     pö
    -0.63
    POSITIVE LOGITS
    oo
    2.38
     impra
    1.93
     maneu
    1.87
     increa
    1.83
     affor
    1.83
     SOO
    1.79
     unden
    1.77
     excru
    1.76
     oleo
    1.75
     GOO
    1.74
    Activations Density 0.239%

    No Known Activations