© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 2027
    Prev
    Next
    INDEX
    Explanations

    concepts related to evolution and adaptation in social contexts

    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
    1842
    +0.17
    0.7%
    872
    +0.17
    0.7%
    1577
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.17
    0.10
    509
    +0.17
    0.09
    1368
    +0.14
    0.05
    Negative Logits
    <bos>
    -1.64
    .
    -0.86
     be
    -0.81
     a
    -0.81
     an
    -0.81
     so
    -0.81
     also
    -0.80
     de
    -0.80
     in
    -0.79
     
    -0.79
    POSITIVE LOGITS
     swarovski
    2.51
     wien
    2.50
     napoli
    2.40
     milano
    2.39
     lidl
    2.36
     stockholm
    2.35
     maroc
    2.30
     bordeaux
    2.27
     bandung
    2.27
     ecru
    2.25
    Activations Density 1.082%

    No Known Activations