© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2467
    Prev
    Next
    INDEX
    Explanations

    discussions regarding memory and its retrieval processes in a psychological context

    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
    +0.34
    1.4%
    283
    +0.11
    0.4%
    1499
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.34
    0.08
    283
    +0.11
    0.01
    876
    +0.10
    -0.02
    Negative Logits
    <bos>
    -1.85
     themselves
    -0.72
     itself
    -0.70
    <tfoot>
    -0.69
    ⓧ
    -0.67
     himself
    -0.67
     or
    -0.66
     yourself
    -0.66
     обов
    -0.65
     get
    -0.64
    POSITIVE LOGITS
     maneu
    2.34
     increa
    2.32
     effe
    2.27
     accla
    2.26
     disagre
    2.25
     emphat
    2.20
     inev
    2.17
     thut
    2.15
     guarante
    2.15
     „,
    2.09
    Activations Density 0.678%

    No Known Activations