© 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. 14228
    Prev
    Next
    INDEX
    Explanations

    technical terms related to thermodynamics and energy efficiency

    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
    876
    +0.24
    0.8%
    1842
    +0.18
    0.6%
    1499
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.24
    0.12
    1842
    +0.18
    0.09
    876
    +0.18
    -0.03
    Negative Logits
    GOTREF
    -0.78
    currentColor
    -0.71
    الدراسه
    -0.70
    StructEnd
    -0.69
    Ikus
    -0.69
    fvar
    -0.68
    ParallelGroup
    -0.67
    TagHelper
    -0.65
    ,”
    -0.64
    makeConstraints
    -0.64
    POSITIVE LOGITS
     ftu
    2.42
     effe
    2.42
     increa
    2.41
     thut
    2.39
     fta
    2.33
     inev
    2.27
     disagre
    2.27
     aen
    2.23
     fte
    2.23
     secon
    2.20
    Activations Density 1.808%

    No Known Activations