© 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. 4380
    Prev
    Next
    INDEX
    Explanations

    phrases related to global attention or significance

    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
    1129
    +0.10
    0.3%
    764
    +0.09
    0.3%
    856
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.10
    0.04
    1129
    +0.09
    0.05
    1586
    +0.09
    0.04
    Negative Logits
     kram
    -1.13
     glan
    -1.02
     bayern
    -0.96
     ohr
    -0.91
     meis
    -0.91
     myn
    -0.90
     siff
    -0.90
     franz
    -0.90
     „,
    -0.89
     stik
    -0.87
    POSITIVE LOGITS
    paddingVertical
    0.55
    częściej
    0.53
    marginHorizontal
    0.50
    marginVertical
    0.50
    lepiej
    0.49
    Appellee
    0.47
    ⓧ
    0.47
    İyi
    0.47
    onekana
    0.46
     global
    0.45
    Activations Density 0.428%

    No Known Activations