Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1737
    Prev
    Next
    INDEX
    Explanations

    references to flowers, blossoms, and petals in a detailed scientific context

    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
    314
    +0.15
    0.5%
    1865
    +0.12
    0.4%
    201
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.15
    0.02
    201
    +0.12
    0.01
    1331
    +0.12
    0.02
    Negative Logits
     Septembre
    -0.76
     noix
    -0.70
    Demografía
    -0.70
     Novembre
    -0.68
     meras
    -0.67
     vinil
    -0.67
     Octobre
    -0.67
     sés
    -0.67
     asisten
    -0.65
     cannes
    -0.63
    POSITIVE LOGITS
     flowers
    1.22
     flower
    1.21
     Flower
    1.08
    Flowers
    1.08
     Flowers
    1.07
    Flower
    1.06
    flowers
    1.02
    flower
    1.00
     floral
    0.91
     bloom
    0.85
    Activations Density 0.121%

    No Known Activations