© 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. 14364
    Prev
    Next
    INDEX
    Explanations

    descriptions of flavors and ingredients in a food or drink

    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
    1577
    +0.18
    0.5%
    1343
    +0.17
    0.5%
    453
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.18
    0.04
    453
    +0.17
    0.03
    184
    +0.11
    0.01
    Negative Logits
     ftu
    -1.41
     fta
    -1.35
     thut
    -1.25
     poff
    -1.25
     Souha
    -1.23
     ftill
    -1.22
     »>
    -1.21
     feen
    -1.21
     hcm
    -1.21
     vns
    -1.20
    POSITIVE LOGITS
     
    0.57
      
    0.57
     -
    0.56
     etc
    0.55
     –
    0.55
    …
    0.54
    <eos>
    0.53
    <strong>
    0.53
     (
    0.53
    ↵
    0.53
    Activations Density 0.129%

    No Known Activations