© 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. 805
    Prev
    Next
    INDEX
    Explanations

    sentences that start with 'it's a'

    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
    382
    +0.17
    0.5%
    381
    +0.11
    0.3%
    1961
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.17
    0.05
    1705
    +0.11
    0.05
    468
    +0.11
    0.04
    Negative Logits
     tramonto
    -1.18
     Châ
    -1.12
     Luglio
    -1.12
     jaya
    -1.09
     exécu
    -1.08
     Meksi
    -1.07
     Settembre
    -1.07
     Aéroport
    -1.06
     épis
    -1.06
     rafra
    -1.05
    POSITIVE LOGITS
     great
    0.71
     good
    0.70
     shame
    0.69
     reminder
    0.69
     bit
    0.68
     hard
    0.67
     sad
    0.67
     nice
    0.67
     difficult
    0.66
     lot
    0.66
    Activations Density 0.216%

    No Known Activations