© 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. 4121
    Prev
    Next
    INDEX
    Explanations

    musical terms and 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
    1842
    +0.27
    1.1%
    1577
    +0.25
    1.0%
    394
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.27
    0.11
    394
    +0.25
    0.09
    1314
    +0.18
    0.09
    Negative Logits
    <bos>
    -0.50
     attorno
    -0.47
    Abbiamo
    -0.44
    ManagedBean
    -0.44
     statunit
    -0.42
    reportWebVitals
    -0.42
     accanto
    -0.41
     nuovamente
    -0.41
     specialmente
    -0.40
    קישורים
    -0.40
    POSITIVE LOGITS
     heapq
    0.65
     ftu
    0.60
    «<
    0.59
     fhort
    0.58
     fup
    0.57
     tranf
    0.55
     ftill
    0.55
     »>
    0.54
     thut
    0.52
     fuper
    0.51
    Activations Density 1.957%

    No Known Activations