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. 714
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating performance metrics in a sports context

    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
    0.7%
    297
    +0.10
    0.4%
    453
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1905
    +0.20
    0.07
    297
    +0.10
    0.07
    776
    +0.10
    0.07
    Negative Logits
    <bos>
    -1.51
    ⓧ
    -0.77
     république
    -0.74
     OnTrigger
    -0.72
     embodi
    -0.71
     anhyd
    -0.67
     liberality
    -0.66
     "@/
    -0.65
     lamella
    -0.65
     lavorato
    -0.65
    POSITIVE LOGITS
     kosme
    1.06
     akut
    1.03
     kriminal
    1.03
     silikon
    1.03
     protokol
    1.00
     kompres
    0.99
     konserv
    0.94
     radikal
    0.93
     kooper
    0.93
     keram
    0.92
    Activations Density 0.560%

    No Known Activations