© 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. 1557
    Prev
    Next
    INDEX
    Explanations

    repeated phrases and key conjunctions indicating relevance or emphasis in discourse

    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
    +0.43
    2.1%
    1741
    +0.20
    1.0%
    2019
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.43
    0.10
    1967
    +0.20
    0.10
    678
    +0.14
    0.09
    Negative Logits
    <bos>
    -3.01
    //////////////
    -0.64
    ////////
    -0.63
    //////////
    -0.63
    /////////////
    -0.63
     and
    -0.62
                    
    -0.57
    ,
    -0.56
    ///////////////
    -0.56
    <eos>
    -0.55
    POSITIVE LOGITS
     Minang
    1.44
     bandung
    1.38
     magis
    1.30
     sappi
    1.25
     cæ
    1.25
     santiago
    1.23
     Banjar
    1.22
     Jambi
    1.19
     tramont
    1.18
     italia
    1.18
    Activations Density 0.897%

    No Known Activations