© 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. 4154
    Prev
    Next
    INDEX
    Explanations

    keywords related to gardening and urban planning

    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
    1978
    +0.13
    0.4%
    1031
    +0.11
    0.3%
    644
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1031
    +0.13
    0.06
    862
    +0.11
    0.03
    644
    +0.07
    0.05
    Negative Logits
     Walkover
    -0.65
     PicClick
    -0.59
     universale
    -0.57
    MigrationBuilder
    -0.57
     bont
    -0.57
     utop
    -0.55
     moza
    -0.55
    StoryboardSegue
    -0.54
     éte
    -0.54
     referenties
    -0.53
    POSITIVE LOGITS
     ingrat
    0.61
     available
    0.57
     involved
    0.53
     impractica
    0.52
    Wię
    0.52
    Jakie
    0.51
    Przyp
    0.51
     hearers
    0.49
     Dijo
    0.49
    Dzięki
    0.48
    Activations Density 0.371%

    No Known Activations