© 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. 12552
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms and concepts

    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
    674
    +0.23
    0.8%
    764
    +0.20
    0.7%
    198
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.23
    0.06
    198
    +0.20
    0.05
    81
    +0.16
    0.02
    Negative Logits
     unspeak
    -1.39
     shenan
    -1.36
     indescri
    -1.27
     impra
    -1.21
     horrend
    -1.18
     uninten
    -1.15
     apprehen
    -1.14
     disreg
    -1.13
     disagre
    -1.13
     reluct
    -1.11
    POSITIVE LOGITS
     Ause
    0.81
    Portale
    0.66
    Portály
    0.63
    expandindo
    0.63
     referenties
    0.62
     AspNetCore
    0.62
    Sqft
    0.62
     PeEnEo
    0.62
     muualla
    0.61
    bitat
    0.59
    Activations Density 0.588%

    No Known Activations