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. 1095
    Prev
    Next
    INDEX
    Explanations

    instances of recent events or updates

    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
    +0.40
    1.8%
    1842
    +0.12
    0.5%
    2019
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.40
    0.09
    2034
    +0.12
    0.09
    382
    +0.08
    0.07
    Negative Logits
    <bos>
    -2.13
    ⓧ
    -0.94
    
    
    -0.73
    /**
    -0.68
     SIMBAD
    -0.61
    IsContent
    -0.60
     ProtoMessage
    -0.60
     onCancelled
    -0.59
    ConstraintMaker
    -0.58
    TagMode
    -0.58
    POSITIVE LOGITS
     Keny
    1.22
     maneu
    1.13
     Jambi
    1.12
     véhic
    1.10
     accla
    1.03
     Pekan
    1.02
     Minang
    1.02
     Banjar
    1.01
     Khart
    1.01
     Palembang
    1.00
    Activations Density 1.115%

    No Known Activations