© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11620
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistics and numbers

    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
    +0.18
    0.6%
    1253
    +0.13
    0.4%
    1984
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.18
    0.06
    1984
    +0.13
    0.06
    732
    +0.10
    0.05
    Negative Logits
    <bos>
    -0.75
    reszcie
    -0.68
     virtù
    -0.66
    ==""){
    -0.66
    vece
    -0.64
    idać
    -0.63
    Personendaten
    -0.62
    PerformLayout
    -0.62
     تانيه
    -0.60
     linkovi
    -0.59
    POSITIVE LOGITS
     lele
    1.01
     seiz
    0.96
     fep
    0.94
     hcm
    0.94
     Kün
    0.93
     secon
    0.92
     kug
    0.92
     reluct
    0.91
     umo
    0.90
     Juf
    0.90
    Activations Density 0.334%

    No Known Activations