© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4859
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate direction or progression

    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
    +0.25
    1.0%
    1520
    +0.12
    0.5%
    1222
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1222
    +0.25
    0.02
    1520
    +0.12
    0.02
    1557
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.16
    /***
    -0.87
    <?
    -0.60
    ///**
    -0.60
    ⓧ
    -0.58
    MockBean
    -0.58
    GenerationType
    -0.58
    /**
    -0.57
    Kontrola
    -0.56
    <!--<
    -0.55
    POSITIVE LOGITS
     churrasco
    1.13
     maroc
    1.11
     paradiso
    1.09
     signora
    1.09
     papà
    1.07
     cioc
    1.03
     riviera
    1.02
     bordeaux
    1.02
     swarovski
    1.00
     signore
    0.99
    Activations Density 0.059%

    No Known Activations