© 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. 1425
    Prev
    Next
    INDEX
    Explanations

    references to snow and snowfall

    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
    +0.20
    1.1%
    1124
    +0.13
    0.7%
    1044
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.20
    0.02
    1964
    +0.13
    0.02
    1124
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.48
    ⓧ
    -0.87
    <?
    -0.81
    /**
    -0.76
    SequentialGroup
    -0.73
    public
    -0.69
    /*++
    -0.68
    RepeatedField
    -0.67
    PutMapping
    -0.66
    Билгалдахарш
    -0.65
    POSITIVE LOGITS
     maneu
    1.67
     emphat
    1.63
     Minang
    1.61
     indestru
    1.60
     Juf
    1.57
     disagre
    1.55
     impra
    1.54
     unwarran
    1.54
     bandung
    1.51
     excru
    1.51
    Activations Density 0.036%

    No Known Activations