© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 11830
    Prev
    Next
    INDEX
    Explanations

    information about the acquisition and development of parcels of land

    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
    1842
    +0.16
    0.5%
    738
    +0.12
    0.3%
    1385
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.16
    0.06
    1013
    +0.12
    0.06
    107
    +0.11
    0.05
    Negative Logits
     emphat
    -1.01
     alre
    -0.94
     disagre
    -0.94
     volunte
    -0.91
     effe
    -0.91
     reluct
    -0.89
     accla
    -0.89
     attemp
    -0.88
     maneu
    -0.88
     coö
    -0.88
    POSITIVE LOGITS
    AndEndTag
    0.62
     purposes
    0.56
     visitors
    0.55
     activities
    0.53
     needs
    0.50
     Tenis
    0.49
     relocated
    0.47
     storage
    0.47
    garder
    0.46
     amenities
    0.46
    Activations Density 0.550%

    No Known Activations