© 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. 11901
    Prev
    Next
    INDEX
    Explanations

    technical details and updates related to software development or game design

    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
    1385
    +0.14
    0.4%
    690
    +0.14
    0.4%
    678
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.05
    1666
    +0.14
    0.03
    1307
    +0.10
    0.02
    Negative Logits
     akut
    -1.03
     praktik
    -0.93
     radikal
    -0.93
     kollek
    -0.86
     silikon
    -0.85
     demokra
    -0.82
     elektronik
    -0.81
     disiplin
    -0.81
     optik
    -0.81
     kosme
    -0.80
    POSITIVE LOGITS
     itemList
    0.73
     itemName
    0.70
     tagName
    0.70
     liberality
    0.69
     userEmail
    0.69
     imagePath
    0.68
     tricot
    0.68
     objs
    0.67
     realism
    0.67
     felicity
    0.66
    Activations Density 0.540%

    No Known Activations