© 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. 12684
    Prev
    Next
    INDEX
    Explanations

    SQL statements related to database table creation and manipulation

    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
    876
    +0.17
    0.5%
    81
    +0.10
    0.3%
    906
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.17
    0.00
    1317
    +0.10
    0.03
    441
    +0.10
    0.02
    Negative Logits
    Net
    -0.59
    UniformLocation
    -0.59
    系统
    -0.58
    Capacidad
    -0.58
    消息
    -0.58
    '][$
    -0.57
    invokeLater
    -0.57
    Celular
    -0.56
     воен
    -0.56
    这是
    -0.56
    POSITIVE LOGITS
     increa
    2.14
     guarante
    2.02
     affor
    1.98
     emphat
    1.94
     purcha
    1.92
     effe
    1.92
     embra
    1.91
     ?...
    1.90
     strick
    1.86
     reluct
    1.85
    Activations Density 0.181%

    No Known Activations