© 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. 7763
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Greece

    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
    228
    +0.19
    0.6%
    1983
    +0.12
    0.4%
    1065
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    228
    +0.19
    0.04
    1065
    +0.12
    0.03
    1983
    +0.11
    0.03
    Negative Logits
    Τι
    -0.73
    Για
    -0.65
    OGND
    -0.65
    FieldDescriptor
    -0.64
    createNewFile
    -0.60
     disambiguazione
    -0.60
    Horário
    -0.60
    ஒ
    -0.59
    DoubleQuotes
    -0.59
     وتسجيلات
    -0.59
    POSITIVE LOGITS
     hentai
    1.43
     greek
    1.35
     milf
    1.31
     depic
    1.29
     shenan
    1.28
     greece
    1.23
     snoopy
    1.21
     GREEK
    1.20
     Grecian
    1.19
     strick
    1.19
    Activations Density 0.177%

    No Known Activations