© 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. 1584
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names (including 'Bradley')

    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
    1178
    +0.11
    0.3%
    331
    +0.10
    0.3%
    1047
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.11
    0.03
    184
    +0.10
    0.01
    1120
    +0.10
    0.03
    Negative Logits
     trovar
    -0.68
     altrett
    -0.68
     soggior
    -0.68
     gius
    -0.67
     abiti
    -0.65
     rispar
    -0.64
     affatto
    -0.64
    jednoc
    -0.63
     saper
    -0.61
     immagin
    -0.61
    POSITIVE LOGITS
     Bradley
    1.83
    Bradley
    1.63
     Fletcher
    0.98
     Barnes
    0.87
     fountain
    0.77
    Fletcher
    0.76
    Barnes
    0.73
     fountains
    0.72
     Fountain
    0.72
     patron
    0.69
    Activations Density 0.222%

    No Known Activations