© 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. 1950
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving or finding solutions

    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
    817
    +0.09
    0.3%
    92
    +0.09
    0.3%
    490
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1519
    +0.09
    0.04
    1864
    +0.09
    0.03
    1826
    +0.08
    0.01
    Negative Logits
     emphat
    -1.53
     accla
    -1.48
     increa
    -1.48
     maneu
    -1.46
     reluct
    -1.42
     suscep
    -1.40
     purcha
    -1.40
     strick
    -1.40
     inev
    -1.38
     affor
    -1.37
    POSITIVE LOGITS
     ways
    0.87
    ways
    0.73
     way
    0.70
     how
    0.65
    way
    0.64
    égias
    0.63
     Ways
    0.62
     to
    0.59
     fit
    0.58
    GIH
    0.55
    Activations Density 0.241%

    No Known Activations