© 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. 4648
    Prev
    Next
    INDEX
    Explanations

    references to outdoor spaces or specific locations like a patio or a side of a city

    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
    1013
    +0.24
    0.8%
    964
    +0.11
    0.4%
    906
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.24
    0.07
    964
    +0.11
    0.04
    1804
    +0.09
    0.04
    Negative Logits
    XmlEnum
    -0.70
     Ibidem
    -0.61
     pymysql
    -0.60
     nicolas
    -0.55
     simplif
    -0.54
     Præ
    -0.52
     sapin
    -0.52
     emphat
    -0.51
     Při
    -0.51
     Když
    -0.51
    POSITIVE LOGITS
     outdoor
    0.77
     lawn
    0.71
    outdoor
    0.68
     picnic
    0.68
     patio
    0.67
     lawns
    0.66
     outdoors
    0.65
     park
    0.65
     patios
    0.63
     landscaped
    0.63
    Activations Density 0.386%

    No Known Activations