Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1851
    Prev
    Next
    INDEX
    Explanations

    references to specific animal species and musical genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    0.7%
    1438
    +0.12
    0.5%
    1385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.17
    0.07
    1978
    +0.12
    0.06
    1987
    +0.11
    0.05
    Negative Logits
    <bos>
    -1.77
     كومونز
    -1.19
    PerformLayout
    -1.09
     AssemblyCompany
    -1.09
    GEBURTSDATUM
    -1.09
    TagMode
    -1.07
    RTLR
    -1.06
    ValueStyle
    -1.01
     invokingState
    -0.99
    QMetaType
    -0.99
    POSITIVE LOGITS
     increa
    1.99
     reluct
    1.98
     disagre
    1.96
     indestru
    1.95
     impra
    1.93
     unden
    1.86
     suscep
    1.86
     inev
    1.85
     maneu
    1.81
     excru
    1.80
    Activations Density 0.384%

    No Known Activations