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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3616
    Prev
    Next
    INDEX
    Explanations

    phrases related to literature and philosophical concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    812
    +0.11
    0.4%
    1296
    +0.11
    0.4%
    405
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.11
    0.04
    1296
    +0.11
    0.04
    597
    +0.11
    0.03
    Negative Logits
     vnd
    -0.71
     meis
    -0.66
     „,
    -0.60
     riva
    -0.58
    eeeeeeee
    -0.57
     luxem
    -0.56
     alha
    -0.56
     istr
    -0.56
    hoho
    -0.55
     vj
    -0.55
    POSITIVE LOGITS
     world
    1.03
    world
    0.99
     World
    0.97
    World
    0.95
     WORLD
    0.90
    WORLD
    0.87
     worlds
    0.83
     Worlds
    0.72
    worlds
    0.71
    getWorld
    0.70
    Activations Density 0.084%

    No Known Activations