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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15029
    Prev
    Next
    INDEX
    Explanations

    information related to environmental conservation and gardening tips

    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
    1842
    +0.10
    0.3%
    1675
    +0.09
    0.3%
    455
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    809
    +0.10
    0.06
    677
    +0.09
    0.04
    1675
    +0.09
    0.06
    Negative Logits
     katal
    -0.57
     karton
    -0.57
    PerformLayout
    -0.55
     kade
    -0.54
     makro
    -0.54
     kristal
    -0.53
     benzin
    -0.53
     kask
    -0.53
     moza
    -0.51
     alip
    -0.50
    POSITIVE LOGITS
     astronauts
    0.60
     Belén
    0.57
     astronaut
    0.54
     barbacoa
    0.54
     missions
    0.53
     Almería
    0.52
     manned
    0.51
     spacecraft
    0.50
     Estación
    0.49
     expeditions
    0.49
    Activations Density 0.555%

    No Known Activations