Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6780
    Prev
    Next
    INDEX
    Explanations

    references to high-definition (HD) media or content

    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
    +0.20
    1.0%
    1271
    +0.15
    0.8%
    1047
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.20
    0.02
    1271
    +0.15
    0.01
    1385
    +0.15
    0.02
    Negative Logits
    <bos>
    -2.11
    messageInfo
    -0.73
    Rohy
    -0.65
    GroupLayout
    -0.59
    
    
    -0.59
    /*
    -0.58
    ⓧ
    -0.57
    UnitTesting
    -0.57
     ivelany
    -0.57
    Abitanti
    -0.57
    POSITIVE LOGITS
     rodriguez
    1.14
     HD
    1.13
     claudia
    1.12
     valencia
    1.11
     lorenzo
    1.09
     bandung
    1.08
     maroc
    1.07
     lyon
    1.07
     marseille
    1.06
     aen
    1.05
    Activations Density 0.068%

    No Known Activations