© 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. 3599
    Prev
    Next
    INDEX
    Explanations

    information related to energy production and distribution

    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
    1120
    +0.14
    0.4%
    1385
    +0.11
    0.3%
    121
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.14
    0.05
    939
    +0.11
    0.04
    1948
    +0.10
    0.04
    Negative Logits
     zyn
    -0.70
     juf
    -0.69
     handels
    -0.64
     nadru
    -0.64
     krab
    -0.63
     theolog
    -0.63
     NSCoder
    -0.58
     gero
    -0.58
     Godt
    -0.58
     imago
    -0.57
    POSITIVE LOGITS
     electricity
    0.85
     Electricity
    0.75
     kWh
    0.68
    Electricity
    0.68
    electricity
    0.63
    kWh
    0.63
     megane
    0.58
     power
    0.58
     outages
    0.58
     electrical
    0.57
    Activations Density 0.299%

    No Known Activations