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. 13431
    Prev
    Next
    INDEX
    Explanations

    words related to regulations and standards, specifically in the context of robotics and surveillance

    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
    939
    +0.09
    0.3%
    946
    +0.08
    0.2%
    177
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.09
    0.05
    939
    +0.08
    0.06
    392
    +0.08
    0.03
    Negative Logits
     impra
    -0.96
    ;;)
    -0.95
     disreg
    -0.88
     Româ
    -0.80
    YMMV
    -0.80
     poichè
    -0.79
     affor
    -0.77
     manqué
    -0.74
     rheumatism
    -0.74
     Că
    -0.74
    POSITIVE LOGITS
     antigu
    0.53
    Sqft
    0.51
    ഉ
    0.50
     handling
    0.50
    jgl
    0.49
    StackSize
    0.49
     dealings
    0.48
     وتسجيلات
    0.48
    modelBuilder
    0.47
     how
    0.47
    Activations Density 0.419%

    No Known Activations