© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 311
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or associations involved in collaborative efforts

    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
    50
    +0.35
    1.5%
    752
    +0.13
    0.6%
    227
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.35
    0.06
    2019
    +0.13
    0.07
    1042
    +0.13
    0.06
    Negative Logits
    <bos>
    -2.65
    ⓧ
    -0.81
     viewDidLoad
    -0.70
     onView
    -0.69
    /**
    -0.68
     viewWillAppear
    -0.65
     onPause
    -0.62
     onStop
    -0.60
     immer
    -0.60
    lateinit
    -0.59
    POSITIVE LOGITS
     Juf
    1.76
     lele
    1.59
     Khart
    1.53
     délib
    1.48
     véhic
    1.46
     Keny
    1.46
     accla
    1.43
     Minang
    1.41
     Karakter
    1.41
     Præ
    1.40
    Activations Density 0.693%

    No Known Activations