© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7040
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to companies or individuals involved in various industries

    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
    1276
    +0.14
    0.6%
    1438
    +0.14
    0.6%
    1961
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.11
    1177
    +0.14
    0.04
    1363
    +0.14
    0.07
    Negative Logits
    s
    -1.01
    i
    -0.97
    y
    -0.93
    ه
    -0.93
    t
    -0.90
    u
    -0.88
    ה
    -0.86
    n
    -0.86
    a
    -0.85
    e
    -0.85
    POSITIVE LOGITS
     impra
    2.69
     increa
    2.65
     indestru
    2.60
     accla
    2.54
     inev
    2.49
     stockholm
    2.48
     reluct
    2.46
     shenan
    2.45
     strick
    2.43
     intermitt
    2.42
    Activations Density 0.958%

    No Known Activations