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. 700
    Prev
    Next
    INDEX
    Explanations

    phrases that convey complexity or depth in discussion

    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
    +0.27
    1.2%
    1013
    +0.10
    0.5%
    2015
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1871
    +0.27
    0.08
    1380
    +0.10
    0.02
    1839
    +0.10
    0.12
    Negative Logits
    <bos>
    -1.42
     SEDS
    -0.90
     bronz
    -0.81
    íí
    -0.79
    ാൻ
    -0.75
    CppCodeGen
    -0.74
    RegressionTest
    -0.74
     demografica
    -0.74
     prioritize
    -0.73
     intptr
    -0.72
    POSITIVE LOGITS
     shenan
    1.47
     milf
    1.46
     wikihow
    1.46
     hentai
    1.40
     simpsons
    1.28
     genshin
    1.27
     felipe
    1.25
     :'(
    1.25
     lmfao
    1.25
     destinées
    1.24
    Activations Density 11.020%

    No Known Activations