© 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. 13471
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code snippets

    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
    876
    +0.24
    0.8%
    1177
    +0.21
    0.7%
    678
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.24
    0.07
    876
    +0.21
    -0.00
    1871
    +0.16
    0.05
    Negative Logits
     He
    -0.96
     His
    -0.90
    <eos>
    -0.88
     But
    -0.88
    Crítica
    -0.87
    Rusia
    -0.86
    Además
    -0.85
     وَ
    -0.85
     May
    -0.84
     More
    -0.84
    POSITIVE LOGITS
     increa
    3.30
     effe
    3.25
     !...
    3.18
     ?...
    3.17
     fta
    3.13
     suscep
    3.06
     ftu
    3.05
     inev
    3.04
     desir
    3.04
     thut
    3.04
    Activations Density 0.438%

    No Known Activations