© 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. 438
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing extremity or heightened states

    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
    +0.23
    1.0%
    1482
    +0.13
    0.6%
    341
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1482
    +0.23
    0.07
    201
    +0.13
    0.05
    893
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.30
    Vegeu
    -0.72
    /**
    -0.68
    ⓧ
    -0.68
    Argumento
    -0.68
    Autoritní
    -0.63
    Mein
    -0.61
    <tfoot>
    -0.60
    glMatrixMode
    -0.60
    /***
    -0.58
    POSITIVE LOGITS
     bandung
    1.40
     murano
    1.36
     stockholm
    1.35
     lamborghini
    1.34
     ecru
    1.33
     maneu
    1.30
     milf
    1.30
     lidl
    1.27
     beverly
    1.27
     santiago
    1.26
    Activations Density 0.072%

    No Known Activations