© 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. 14689
    Prev
    Next
    INDEX
    Explanations

    mentions of physical locations, particularly cities and landmarks

    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
    382
    +0.22
    0.7%
    1741
    +0.16
    0.5%
    2034
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.22
    0.10
    1265
    +0.16
    0.06
    736
    +0.12
    0.07
    Negative Logits
     meras
    -0.98
     marte
    -0.95
     alkoh
    -0.95
     praktik
    -0.95
     balon
    -0.94
     parati
    -0.94
     medes
    -0.93
     sement
    -0.93
     ideolog
    -0.92
     kosme
    -0.92
    POSITIVE LOGITS
     followed
    0.75
     plus
    0.70
    以及
    0.70
     그리고
    0.69
     and
    0.69
     which
    0.67
     along
    0.64
     oraz
    0.62
     coupled
    0.62
     sowie
    0.62
    Activations Density 0.412%

    No Known Activations