© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14394
    Prev
    Next
    INDEX
    Explanations

    countries and political terms related to sovereignty and disputes

    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
    1317
    +0.10
    0.3%
    1870
    +0.10
    0.3%
    402
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.10
    0.04
    402
    +0.10
    0.06
    41
    +0.10
    0.06
    Negative Logits
     secon
    -1.24
     aen
    -1.22
     fte
    -1.16
     stockholm
    -1.14
     hcm
    -1.14
     mef
    -1.14
     fta
    -1.11
     reluct
    -1.11
     effe
    -1.11
     lill
    -1.10
    POSITIVE LOGITS
    rlrl
    0.73
     الحره
    0.59
    apimachinery
    0.57
    Bekijk
    0.55
    Skocz
    0.55
    '
    0.55
    thâu
    0.54
    Hochspringen
    0.54
    Leider
    0.53
    ATEGY
    0.52
    Activations Density 0.417%

    No Known Activations