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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7750
    Prev
    Next
    INDEX
    Explanations

    questions related to location and existence

    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
    1174
    +0.08
    0.2%
    1840
    +0.08
    0.2%
    468
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    763
    +0.08
    0.03
    1483
    +0.08
    0.03
    2025
    +0.07
    0.03
    Negative Logits
     disreg
    -1.07
     impra
    -0.99
     pymysql
    -0.98
     tolerably
    -0.95
     uninten
    -0.94
     suscep
    -0.93
     lamborghini
    -0.92
    Hahahahaha
    -0.91
     encomp
    -0.90
     outlander
    -0.90
    POSITIVE LOGITS
    IsContent
    0.78
    piram
    0.74
    setVerticalGroup
    0.72
    RTEX
    0.70
    IndentedString
    0.69
    writeFieldEnd
    0.68
     betweenstory
    0.67
     himo
    0.67
     Où
    0.67
    DotNetBar
    0.66
    Activations Density 0.139%

    No Known Activations