© 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. 4258
    Prev
    Next
    INDEX
    Explanations

    terms related to the importance of various actions or decisions

    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
    573
    +0.09
    0.3%
    80
    +0.09
    0.3%
    1372
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2030
    +0.09
    0.02
    1992
    +0.09
    0.02
    1372
    +0.08
    0.03
    Negative Logits
     uhr
    -1.11
     kram
    -1.09
     praktik
    -1.02
     alkoh
    -1.01
     naer
    -1.00
     utop
    -0.99
     kado
    -0.98
     saar
    -0.97
     meis
    -0.96
     bayern
    -0.94
    POSITIVE LOGITS
     importance
    0.93
    importance
    0.84
     Importance
    0.81
    Importance
    0.77
     significance
    0.70
    NewUrlParser
    0.65
     of
    0.61
    Significance
    0.59
    ViewFeatures
    0.56
    ificance
    0.55
    Activations Density 0.102%

    No Known Activations