© 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. 1074
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "ADD"

    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
    1296
    +0.10
    0.3%
    1961
    +0.08
    0.2%
    950
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.06
    283
    +0.08
    0.02
    1927
    +0.08
    0.06
    Negative Logits
    setInt
    -0.65
     ao
    -0.64
     com
    -0.63
     bien
    -0.62
    Chỉ
    -0.61
     ac
    -0.61
    Componentes
    -0.58
    Bibliografía
    -0.57
     الحره
    -0.57
    Seguro
    -0.56
    POSITIVE LOGITS
     thut
    1.70
     Mlle
    1.61
     !...
    1.53
     Messieurs
    1.52
     stockholm
    1.50
     increa
    1.49
     unden
    1.48
     fta
    1.47
     napoli
    1.45
     Mère
    1.45
    Activations Density 0.352%

    No Known Activations