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. 1201
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to methods and data collection

    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
    +0.35
    1.3%
    1510
    +0.10
    0.4%
    1265
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1820
    +0.35
    0.04
    1871
    +0.10
    0.03
    504
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.48
    <?
    -1.04
     intersper
    -0.89
    
    
    -0.84
    ⓧ
    -0.82
     négociations
    -0.75
     encomp
    -0.74
    /**
    -0.72
     réunions
    -0.71
     disambigu
    -0.69
    POSITIVE LOGITS
     vasi
    0.82
     riva
    0.79
     parati
    0.79
     torba
    0.74
     Muhamma
    0.74
     makam
    0.73
     tenda
    0.72
     BoxFit
    0.72
     maroc
    0.70
     barca
    0.70
    Activations Density 0.238%

    No Known Activations