© 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. 1983
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or formal language, particularly surrounding accusations or actions

    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
    1604
    +0.10
    0.3%
    406
    +0.07
    0.2%
    513
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.03
    184
    +0.07
    0.01
    283
    +0.07
    0.01
    Negative Logits
     pyram
    -0.81
     solidar
    -0.79
     konkre
    -0.78
     praktik
    -0.77
     Antal
    -0.74
     pira
    -0.72
     akut
    -0.71
     templ
    -0.71
     meri
    -0.70
     musli
    -0.70
    POSITIVE LOGITS
    sive
    1.80
    sives
    1.53
    siveness
    1.12
    sion
    1.10
     spacious
    1.01
     Spacious
    1.00
    sively
    0.99
    Spacious
    0.96
     ecru
    0.95
     nutella
    0.93
    Activations Density 0.267%

    No Known Activations