© 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. 12730
    Prev
    Next
    INDEX
    Explanations

    economic terms related to the growth of an economy

    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
    453
    +0.13
    0.4%
    872
    +0.13
    0.4%
    1385
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1809
    +0.13
    0.04
    876
    +0.13
    -0.02
    1368
    +0.12
    0.02
    Negative Logits
     pamph
    -1.38
     shenan
    -1.38
     accla
    -1.33
     reluct
    -1.30
     depic
    -1.30
     encomp
    -1.23
     disagre
    -1.21
     sophistic
    -1.21
     intersper
    -1.21
     apprehen
    -1.20
    POSITIVE LOGITS
    <bos>
    1.28
     usually
    0.67
    jws
    0.58
     typically
    0.55
    usually
    0.55
    تقاوى
    0.54
     lenker
    0.53
     Usually
    0.52
    annica
    0.50
     generally
    0.50
    Activations Density 0.993%

    No Known Activations