© 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. 4712
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing superlatives or rankings related to the world

    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
    +0.29
    1.2%
    421
    +0.11
    0.5%
    1363
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1310
    +0.29
    0.03
    1505
    +0.11
    0.04
    421
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.13
     sond
    -0.61
    梅
    -0.60
    大山
    -0.59
     dras
    -0.57
     handel
    -0.56
    媚
    -0.56
     handels
    -0.56
    鹿
    -0.55
    保安
    -0.55
    POSITIVE LOGITS
     sappi
    1.57
     soggior
    1.47
     ecru
    1.40
     affez
    1.36
     vogli
    1.23
     unlaw
    1.23
     swarovski
    1.23
    capulco
    1.20
     Áng
    1.18
     Luglio
    1.15
    Activations Density 0.081%

    No Known Activations