© 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. 115
    Prev
    Next
    INDEX
    Explanations

    phrases and actions related to problem-solving and figuring things out

    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
    +0.19
    0.8%
    687
    +0.13
    0.5%
    991
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.19
    0.03
    991
    +0.13
    0.03
    82
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.37
    bar
    -0.61
    /***
    -0.60
     promote
    -0.58
    san
    -0.58
    /*!
    -0.57
    
    -0.56
     san
    -0.56
    promote
    -0.55
     promoted
    -0.54
    POSITIVE LOGITS
     épu
    1.25
     ecru
    1.17
     swarovski
    1.14
     carina
    1.12
     délib
    1.11
     tramont
    1.10
     déchir
    1.08
     tolerably
    1.08
     tremb
    1.08
     scrat
    1.07
    Activations Density 0.076%

    No Known Activations