© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3026
    Prev
    Next
    INDEX
    Explanations

    terms related to games and gaming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1842
    +0.17
    0.7%
    50
    +0.14
    0.6%
    394
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.09
    304
    +0.14
    0.00
    283
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.91
     en
    -0.81
     des
    -0.79
     ou
    -0.76
     sur
    -0.75
     qu
    -0.75
     onPause
    -0.75
     de
    -0.74
    ・
    -0.74
     du
    -0.73
    POSITIVE LOGITS
     mef
    2.30
     sergio
    2.26
     fta
    2.24
     wien
    2.21
     affor
    2.21
     inev
    2.20
     volunte
    2.20
     ricardo
    2.19
     hcm
    2.18
     ftu
    2.18
    Activations Density 0.649%

    No Known Activations