© 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. 13265
    Prev
    Next
    INDEX
    Explanations

    descriptions of events or actions involving multiple people

    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
    1535
    +0.25
    0.8%
    2034
    +0.18
    0.6%
    382
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.10
    1535
    +0.18
    0.08
    310
    +0.18
    0.05
    Negative Logits
     abnorm
    -1.51
    Lmfao
    -1.49
     nece
    -1.48
     suspic
    -1.45
     uncin
    -1.44
    Ikr
    -1.41
     thut
    -1.41
     emphat
    -1.40
     antem
    -1.40
    Lma
    -1.39
    POSITIVE LOGITS
    ↵↵
    1.03
    <eos>
    1.03
     But
    0.92
     However
    0.92
    ↵↵↵
    0.92
     Although
    0.90
     This
    0.89
     There
    0.88
     Thus
    0.87
     Then
    0.87
    Activations Density 0.486%

    No Known Activations