Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14033
    Prev
    Next
    INDEX
    Explanations

    countries or regions mentioned within a geopolitical or socio-economic context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1265
    +0.09
    0.3%
    1870
    +0.08
    0.2%
    227
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.09
    0.05
    421
    +0.08
    0.04
    1948
    +0.08
    0.04
    Negative Logits
     ikon
    -0.58
     maga
    -0.57
     Okt
    -0.57
     bont
    -0.56
     dras
    -0.56
     elek
    -0.56
     Obra
    -0.55
     volu
    -0.55
     moza
    -0.55
     pank
    -0.55
    POSITIVE LOGITS
     unwarran
    1.15
     liberality
    0.82
     unspeak
    0.82
     ingrat
    0.80
     countries
    0.79
     ecru
    0.78
     disagre
    0.78
     courtier
    0.76
     indescri
    0.75
     cuck
    0.75
    Activations Density 0.247%

    No Known Activations