© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12648
    Prev
    Next
    INDEX
    Explanations

    types of medical conditions and medication names

    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
    50
    +0.21
    0.6%
    394
    +0.13
    0.4%
    1343
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.21
    0.05
    1108
    +0.13
    0.05
    2002
    +0.13
    0.04
    Negative Logits
    <bos>
    -0.58
    <?
    -0.52
     rattled
    -0.47
     shriek
    -0.47
     ex
    -0.46
     rattling
    -0.46
    бит
    -0.46
     anxiously
    -0.45
     clatter
    -0.45
     rumbling
    -0.45
    POSITIVE LOGITS
     espri
    1.00
     quæ
    0.99
     fatis
    0.91
     particolar
    0.90
     ejus
    0.90
     oleo
    0.89
     nomine
    0.88
     igno
    0.87
     cæ
    0.87
     socie
    0.86
    Activations Density 0.176%

    No Known Activations