© 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. 1039
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters, investigations, and political events

    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
    298
    +0.11
    0.3%
    752
    +0.10
    0.3%
    1177
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.11
    0.04
    1052
    +0.10
    0.04
    376
    +0.10
    0.04
    Negative Logits
    flexGrow
    -0.62
    =="")
    -0.54
    ==""){
    -0.54
    InjectAttribute
    -0.50
    LayoutConstraint
    -0.48
    AccessorTable
    -0.48
    ナブル
    -0.48
    arParams
    -0.48
    參考文獻
    -0.48
    pherd
    -0.47
    POSITIVE LOGITS
     Mlle
    0.87
     swarovski
    0.87
     broderie
    0.86
     Bartholo
    0.84
     Román
    0.83
     Perci
    0.82
     Whence
    0.81
     désert
    0.79
     Adieu
    0.79
     carrefour
    0.79
    Activations Density 0.152%

    No Known Activations