© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 832
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or entity, possibly related to education or community activities

    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
    900
    +0.12
    0.4%
    404
    +0.11
    0.3%
    1323
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.05
    690
    +0.11
    0.04
    1343
    +0.11
    0.04
    Negative Logits
     sa
    -0.73
    lichem
    -0.70
     let
    -0.69
    ێ
    -0.69
      
    -0.69
     со
    -0.68
     pack
    -0.68
     
    -0.67
    .
    -0.67
     so
    -0.67
    POSITIVE LOGITS
     depic
    2.26
     increa
    2.16
     encomp
    2.13
     inev
    2.12
     impra
    2.11
     Lind
    2.10
     disagre
    2.09
     scrat
    2.03
     accla
    2.02
     aen
    2.01
    Activations Density 0.286%

    No Known Activations