© 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. 1928
    Prev
    Next
    INDEX
    Explanations

    references to Creative Commons licenses and associated keywords

    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
    1096
    +0.17
    1.0%
    1124
    +0.15
    0.8%
    506
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1096
    +0.17
    0.02
    1331
    +0.15
    0.02
    1896
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.13
    archiviato
    -0.55
    mergeFrom
    -0.54
     trovano
    -0.54
    lrrr
    -0.53
    руктура
    -0.52
    InjectMocks
    -0.51
     '{@
    -0.50
    Varint
    -0.50
    lrrrr
    -0.50
    POSITIVE LOGITS
     CC
    1.04
     deko
    1.03
     vne
    1.01
     meis
    0.99
     effe
    0.97
     kram
    0.95
     kasa
    0.95
     wien
    0.94
     affor
    0.94
     cc
    0.93
    Activations Density 0.126%

    No Known Activations