© 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. 6799
    Prev
    Next
    INDEX
    Explanations

    numerical information, ratings, and structured data in a text format

    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
    764
    +0.30
    1.1%
    184
    +0.28
    1.0%
    1842
    +0.21
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.30
    0.04
    764
    +0.28
    0.06
    1842
    +0.21
    0.05
    Negative Logits
     nece
    -0.89
     dispen
    -0.88
     dises
    -0.87
     shur
    -0.86
     solidar
    -0.85
     fta
    -0.84
     dora
    -0.83
     desir
    -0.82
     vogli
    -0.81
     hcm
    -0.81
    POSITIVE LOGITS
     prêtre
    0.51
      
    0.49
    ↵↵
    0.48
    ↵
    0.48
     [
    0.48
     docteur
    0.47
    .”
    0.46
     créateur
    0.45
    ...
    0.45
     
    0.45
    Activations Density 0.580%

    No Known Activations