© 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. 455
    Prev
    Next
    INDEX
    Explanations

    titles of movies and notable film projects

    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
    1842
    +0.18
    0.7%
    1177
    +0.15
    0.6%
    1343
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.18
    0.00
    764
    +0.15
    0.04
    167
    +0.15
    0.04
    Negative Logits
    <bos>
    -2.85
    ⓧ
    -0.99
    <?
    -0.88
    
    
    -0.80
    /**
    -0.79
    parsedMessage
    -0.77
    @[+][
    -0.76
    styleType
    -0.76
     springfox
    -0.71
    #
    -0.71
    POSITIVE LOGITS
     emphat
    2.08
     accla
    1.98
     maneu
    1.96
     depic
    1.92
     indestru
    1.92
     increa
    1.86
     shenan
    1.81
     excru
    1.76
     disagre
    1.75
     milf
    1.72
    Activations Density 0.321%

    No Known Activations