© 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. 1463
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or entities within the text

    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
    +0.22
    1.0%
    453
    +0.10
    0.4%
    1741
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.22
    0.11
    1001
    +0.10
    0.09
    1843
    +0.10
    0.07
    Negative Logits
    <bos>
    -2.31
    ⓧ
    -1.23
    /**
    -0.88
    
    
    -0.88
    <?
    -0.74
     springfox
    -0.73
     disbur
    -0.72
     rehabilitate
    -0.67
     modernize
    -0.66
     thicken
    -0.66
    POSITIVE LOGITS
     seksi
    1.36
     panik
    1.27
     keramik
    1.27
     kosme
    1.26
     silikon
    1.26
     antik
    1.24
     Kategor
    1.23
     karton
    1.22
     maksi
    1.22
     alkoh
    1.21
    Activations Density 0.540%

    No Known Activations