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. 1111
    Prev
    Next
    INDEX
    Explanations

    references to scientific experiments and studies, particularly in a medical or academic 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
    +0.21
    1.3%
    2019
    +0.09
    0.5%
    964
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.21
    0.08
    163
    +0.09
    0.01
    1965
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.81
    ImageContext
    -0.67
    ContentAsync
    -0.61
    DoubleQuotes
    -0.59
    Jeografia
    -0.58
    kháu
    -0.58
     Himo
    -0.57
    tonode
    -0.57
     SEDS
    -0.57
    WriteTagHelper
    -0.57
    POSITIVE LOGITS
     alberto
    1.17
     accla
    1.17
     maneu
    1.16
     roberto
    1.15
     embodi
    1.15
     sergio
    1.14
     impra
    1.12
     cristina
    1.11
     lorenzo
    1.08
     affor
    1.07
    Activations Density 1.955%

    No Known Activations