© 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. 3510
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and experimental data handling

    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
    +0.24
    1.1%
    876
    +0.19
    0.9%
    283
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.24
    0.09
    876
    +0.19
    -0.01
    283
    +0.15
    0.01
    Negative Logits
    <bos>
    -3.05
    ValueGenerated
    -0.70
    相
    -0.69
     wants
    -0.68
    SystemColors
    -0.68
    Já
    -0.68
     want
    -0.67
    HasColumnType
    -0.67
    起
    -0.67
    在
    -0.67
    POSITIVE LOGITS
     maneu
    2.63
     emphat
    2.45
     increa
    2.43
     disagre
    2.39
     effe
    2.39
     aen
    2.31
     guarante
    2.26
     inev
    2.25
     wien
    2.24
     desir
    2.23
    Activations Density 0.771%

    No Known Activations