© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    timestamps denoting specific moments within a sequence

    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
    736
    +0.22
    0.8%
    876
    +0.20
    0.7%
    2019
    +0.20
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.22
    0.07
    382
    +0.20
    0.05
    50
    +0.20
    0.06
    Negative Logits
     silikon
    -1.71
     karton
    -1.66
     kompres
    -1.65
     mikrofon
    -1.57
     kosme
    -1.56
     kön
    -1.54
     vertik
    -1.49
     dör
    -1.48
     akut
    -1.47
     kompati
    -1.46
    POSITIVE LOGITS
    Dlaczego
    0.84
    Zgod
    0.83
     discom
    0.80
    Przyp
    0.79
    Gdzie
    0.78
     impover
    0.78
     miscon
    0.74
     endeav
    0.74
    Teraz
    0.74
    Witaj
    0.74
    Activations Density 0.497%

    No Known Activations