© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 157
    Prev
    Next
    INDEX
    Explanations

    numerical values and patterns associated with them

    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
    1343
    +0.46
    1.9%
    184
    +0.23
    1.0%
    1177
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.46
    0.08
    1837
    +0.23
    0.05
    1978
    +0.17
    0.05
    Negative Logits
    <bos>
    -2.83
    商品説明
    -0.90
    hyrchwyd
    -0.85
     Italijani
    -0.80
     <>",
    -0.79
    Diweddarwch
    -0.79
     canlynol
    -0.78
     snippetHide
    -0.76
    setVerticalGroup
    -0.76
     Wiktionnaire
    -0.75
    POSITIVE LOGITS
     quoique
    1.24
     Traité
    1.20
     affor
    1.15
     quelquefois
    1.13
     Cfr
    1.11
     quæ
    1.11
     ?...
    1.11
     habet
    1.07
     Whence
    1.06
     Ibidem
    1.06
    Activations Density 0.072%

    No Known Activations