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. 1857
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or achievements

    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
    +0.32
    1.7%
    122
    +0.15
    0.8%
    528
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.32
    0.05
    528
    +0.15
    0.03
    890
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.52
    ⓧ
    -0.76
    <?
    -0.72
    
    
    -0.61
    /***
    
    -0.61
     intersper
    -0.57
     harmonize
    -0.56
     /**
    
    -0.52
    nehå
    -0.52
     endow
    -0.52
    POSITIVE LOGITS
    ">/
    0.79
    limsy
    0.75
    :"-
    0.74
    gruntled
    0.74
    ]**
    0.73
    ">...
    0.71
     dicono
    0.70
     vanil
    0.70
     chrysler
    0.69
     giù
    0.69
    Activations Density 0.065%

    No Known Activations