© 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. 4348
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and coding practices involving object-oriented concepts

    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
    752
    +0.20
    0.7%
    897
    +0.13
    0.4%
    1984
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.20
    0.09
    314
    +0.13
    0.06
    752
    +0.12
    0.08
    Negative Logits
    <bos>
    -0.81
    Personendaten
    -0.72
    vece
    -0.72
    ==""){
    -0.66
     &___
    -0.65
     attesa
    -0.63
    jsii
    -0.63
    tanooga
    -0.61
     ostavi
    -0.60
     quegli
    -0.60
    POSITIVE LOGITS
     vété
    1.33
     impra
    1.10
     indestru
    1.08
     disreg
    1.07
     intermitt
    1.06
     affor
    1.06
     scrat
    1.05
     uninten
    1.05
     confé
    1.03
     Byp
    1.03
    Activations Density 0.558%

    No Known Activations