© 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. 7111
    Prev
    Next
    INDEX
    Explanations

    numeric values such as measurements or financial figures

    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
    792
    +0.08
    0.2%
    859
    +0.08
    0.2%
    1692
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1578
    +0.08
    0.04
    859
    +0.08
    0.04
    1948
    +0.08
    0.03
    Negative Logits
     Fasc
    -1.29
     aen
    -1.27
     wien
    -1.26
     anton
    -1.25
     Coim
    -1.25
     fta
    -1.24
     socie
    -1.24
     Juf
    -1.22
     franz
    -1.21
     italia
    -1.20
    POSITIVE LOGITS
     ranging
    0.86
    <bos>
    0.73
     exceeding
    0.68
     comparable
    0.67
     equal
    0.66
     seaborn
    0.65
     gik
    0.64
     amounting
    0.64
     equivalent
    0.62
     similar
    0.62
    Activations Density 0.186%

    No Known Activations