© 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 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. 14685
    Prev
    Next
    INDEX
    Explanations

    information related to upgrades and characteristics of units in a video game context

    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
    +0.19
    0.6%
    752
    +0.18
    0.6%
    16
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.19
    0.10
    50
    +0.18
    0.07
    752
    +0.17
    0.06
    Negative Logits
    tổng
    -0.86
    CLUDE
    -0.84
    bài
    -0.84
    CRETE
    -0.83
    một
    -0.82
    部
    -0.82
    CLUD
    -0.81
    cách
    -0.81
    Thành
    -0.81
    FORMANCE
    -0.80
    POSITIVE LOGITS
     vété
    2.46
     confé
    2.25
     fameux
    2.14
     ftu
    2.07
     nôtre
    2.07
     vns
    2.06
     Chapitre
    2.03
     Docteur
    2.01
     fup
    2.01
     fep
    1.99
    Activations Density 0.669%

    No Known Activations