© 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. 12630
    Prev
    Next
    INDEX
    Explanations

    names, likely character names and entities

    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
    662
    +0.20
    0.9%
    204
    +0.18
    0.8%
    251
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.20
    0.04
    204
    +0.18
    0.03
    1805
    +0.15
    0.03
    Negative Logits
     cushi
    -0.48
    withIdentifier
    -0.48
    Arturo
    -0.46
    Życiorys
    -0.45
     Herrick
    -0.45
     Hollis
    -0.45
     vanguard
    -0.44
     equalled
    -0.44
    ınca
    -0.44
     endeavouring
    -0.44
    POSITIVE LOGITS
     Sm
    1.39
    Sm
    1.26
     sm
    1.19
     SM
    1.19
    SM
    1.06
    sm
    1.01
     Luglio
    0.97
     Giugno
    0.81
     Smol
    0.81
     SMI
    0.80
    Activations Density 0.141%

    No Known Activations