© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10669
    Prev
    Next
    INDEX
    Explanations

    terms related to historical facts and locations

    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
    50
    +0.13
    0.4%
    2019
    +0.10
    0.3%
    1921
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.13
    0.07
    1806
    +0.10
    0.06
    1892
    +0.10
    0.05
    Negative Logits
     meras
    -1.23
     kafe
    -1.16
     teras
    -1.14
     alkoh
    -1.13
     elek
    -1.12
     keramik
    -1.10
     optik
    -1.10
     antik
    -1.09
     marte
    -1.09
     ananas
    -1.08
    POSITIVE LOGITS
     intersper
    1.37
     encomp
    1.30
     shenan
    1.24
     downvoted
    1.24
     prolly
    1.20
     reluct
    1.19
     vainly
    1.19
     upvoted
    1.19
     attemp
    1.18
     increa
    1.17
    Activations Density 0.369%

    No Known Activations