© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1707
    Prev
    Next
    INDEX
    Explanations

    terms related to hidden or underlying concepts and mechanisms

    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
    +0.21
    1.1%
    544
    +0.12
    0.6%
    680
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.21
    0.02
    1101
    +0.12
    0.02
    1622
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.61
    /***
    
    -0.64
    HasColumnType
    -0.61
    CreateMap
    -0.57
    define
    -0.56
     engage
    -0.56
     stabilize
    -0.56
    interface
    -0.56
    using
    -0.55
    get
    -0.55
    POSITIVE LOGITS
     Février
    1.28
     Keny
    1.22
     Juillet
    1.17
     thut
    1.15
     Hidden
    1.14
     Décembre
    1.14
     pican
    1.14
     aen
    1.14
     fua
    1.14
     Banjar
    1.13
    Activations Density 0.052%

    No Known Activations