© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13288
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency, power consumption, and operational states of machines

    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
    443
    +0.07
    0.2%
    1980
    +0.06
    0.2%
    1731
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1395
    +0.07
    0.04
    522
    +0.06
    0.04
    1273
    +0.06
    0.02
    Negative Logits
     disagre
    -0.94
     reluct
    -0.92
     fernando
    -0.86
     prouve
    -0.84
     lorenzo
    -0.84
     Souha
    -0.84
     écout
    -0.83
     disgra
    -0.83
     unspeak
    -0.83
     shenan
    -0.83
    POSITIVE LOGITS
     active
    0.82
     actively
    0.76
    active
    0.66
    <bos>
    0.64
     activos
    0.63
     proactive
    0.63
    actively
    0.58
     aggressive
    0.57
     dynamic
    0.57
     lively
    0.55
    Activations Density 0.629%

    No Known Activations