© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7349
    Prev
    Next
    INDEX
    Explanations

    information related to electronic devices, particularly gadgets and technical specifications

    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
    1699
    +0.15
    0.5%
    2034
    +0.13
    0.4%
    16
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2002
    +0.15
    0.03
    81
    +0.13
    0.02
    453
    +0.12
    0.04
    Negative Logits
     silikon
    -1.68
     alkoh
    -1.63
     kompati
    -1.57
     optik
    -1.52
     antik
    -1.50
     makro
    -1.49
     akut
    -1.48
     kosme
    -1.44
     mikrofon
    -1.39
     keramik
    -1.39
    POSITIVE LOGITS
     
    1.48
     $
    0.82
     stickied
    0.77
     upvoted
    0.76
     disreg
    0.75
     horrend
    0.72
     disambigu
    0.71
     downvotes
    0.70
    2
    0.70
     impra
    0.70
    Activations Density 0.282%

    No Known Activations