© 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. 3877
    Prev
    Next
    INDEX
    Explanations

    quantitative information about users, viewers, and attendees in different contexts

    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
    297
    +0.14
    0.4%
    2034
    +0.10
    0.3%
    1177
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.14
    0.07
    870
    +0.10
    0.06
    472
    +0.09
    0.05
    Negative Logits
     ordina
    -1.05
     utop
    -0.98
     nomine
    -0.98
     magis
    -0.98
     meis
    -0.95
     mef
    -0.95
     impon
    -0.94
     ftu
    -0.94
     häm
    -0.92
     spion
    -0.92
    POSITIVE LOGITS
     worldwide
    0.70
     annually
    0.70
     nationwide
    0.57
    worldwide
    0.54
    rufe
    0.53
     globally
    0.52
     across
    0.52
    bonucle
    0.52
     annual
    0.52
     estimated
    0.50
    Activations Density 0.467%

    No Known Activations