© 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. 3987
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and their definitions

    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
    876
    +0.26
    1.1%
    50
    +0.23
    0.9%
    453
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.26
    0.00
    872
    +0.23
    0.06
    1511
    +0.15
    0.02
    Negative Logits
    <bos>
    -3.49
    }],
    -1.03
    Pró
    -1.01
    Siga
    -1.01
    Saiba
    -0.95
    Vegeu
    -0.95
    Conheça
    -0.94
    PutMapping
    -0.94
    Fontes
    -0.91
    Seu
    -0.91
    POSITIVE LOGITS
     increa
    2.71
     maneu
    2.65
     affor
    2.61
     milano
    2.56
     intermitt
    2.53
     guarante
    2.52
     stockholm
    2.43
     reluct
    2.41
     ?...
    2.40
     strick
    2.39
    Activations Density 0.341%

    No Known Activations