© 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. 4585
    Prev
    Next
    INDEX
    Explanations

    quotations and references to statements made by individuals

    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
    +0.21
    0.7%
    1445
    +0.11
    0.3%
    2019
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    873
    +0.21
    0.03
    19
    +0.11
    0.04
    1902
    +0.11
    0.04
    Negative Logits
     ecru
    -0.90
     velour
    -0.89
     amigurumi
    -0.85
     cushi
    -0.81
     hairc
    -0.78
     tupperware
    -0.76
     fuchsia
    -0.72
     burlap
    -0.71
     pewter
    -0.70
     taupe
    -0.70
    POSITIVE LOGITS
     siff
    1.02
     kosme
    1.02
     minimalis
    1.01
     alkoh
    1.00
     akut
    0.99
     keramik
    0.95
     kön
    0.94
     kompati
    0.94
     silikon
    0.93
     sopr
    0.89
    Activations Density 0.102%

    No Known Activations