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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11475
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations or geopolitical events, particularly focusing on the Crimean Peninsula

    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
    50
    +0.13
    0.4%
    1013
    +0.10
    0.3%
    478
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1798
    +0.13
    0.07
    227
    +0.10
    0.08
    1177
    +0.10
    0.04
    Negative Logits
     kado
    -0.75
    ＂
    -0.73
     bunda
    -0.72
     насељу
    -0.69
     uhr
    -0.69
     tí
    -0.66
    CppMethod
    -0.65
    ="">
    -0.65
    osoba
    -0.65
    ുകൾ
    -0.64
    POSITIVE LOGITS
     unspeak
    1.67
     indescri
    1.60
     inconce
    1.45
     impra
    1.44
     milf
    1.43
     indestru
    1.42
     gaily
    1.40
     inappro
    1.40
     intersper
    1.40
     beaute
    1.39
    Activations Density 0.413%

    No Known Activations