© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4249
    Prev
    Next
    INDEX
    Explanations

    references to motivations or reasons behind actions

    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
    +0.23
    1.2%
    1178
    +0.11
    0.6%
    1306
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1950
    +0.23
    0.02
    1306
    +0.11
    0.02
    214
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.84
    /***
    -0.88
    /*!
    -0.81
     harmonize
    -0.63
     enshr
    -0.62
     administer
    -0.59
    panel
    -0.58
     infuse
    -0.58
     abolish
    -0.58
    ⓧ
    -0.57
    POSITIVE LOGITS
     motivation
    1.19
    motivation
    1.11
     Motivation
    1.10
     motivations
    1.09
    Motivation
    1.05
     motiva
    1.02
     swarovski
    1.00
     riva
    0.99
    motivated
    0.96
     Motiv
    0.95
    Activations Density 0.029%

    No Known Activations