© 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. 14583
    Prev
    Next
    INDEX
    Explanations

    laws, rules, and principles mentioned in political contexts

    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
    872
    +0.10
    0.3%
    651
    +0.08
    0.2%
    164
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.10
    0.05
    623
    +0.08
    0.03
    1705
    +0.08
    0.04
    Negative Logits
     hina
    -0.86
     Strukt
    -0.85
     grati
    -0.84
     ille
    -0.82
     gend
    -0.81
     inder
    -0.81
     lele
    -0.80
     rati
    -0.80
     Odys
    -0.79
     priva
    -0.78
    POSITIVE LOGITS
    relenting
    0.87
     rule
    0.76
     principle
    0.72
    mistak
    0.70
    bonsoir
    0.68
    wavering
    0.68
    Rule
    0.66
    sightly
    0.63
     tenet
    0.63
     principles
    0.62
    Activations Density 0.337%

    No Known Activations