Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6844
    Prev
    Next
    INDEX
    Explanations

    references to experience points (XP) and upgrades in gameplay

    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
    +0.29
    1.1%
    876
    +0.11
    0.4%
    1871
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1284
    +0.29
    0.06
    81
    +0.11
    0.06
    792
    +0.08
    0.04
    Negative Logits
    <bos>
    -3.03
    DoubleQuotes
    -1.00
    BufferException
    -0.92
     ***!
    -0.86
    addContainerGap
    -0.82
    ISupport
    -0.82
     NSCoder
    -0.81
    addComponent
    -0.81
     Walkover
    -0.78
    BUYER
    -0.78
    POSITIVE LOGITS
     affor
    2.32
     impra
    2.12
     reluct
    2.07
     increa
    2.06
     resear
    2.02
     disagre
    2.02
     maneu
    1.99
     accla
    1.97
     unlaw
    1.96
     impractica
    1.94
    Activations Density 0.810%

    No Known Activations