Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 967
    Prev
    Next
    INDEX
    Explanations

    terms related to changes in status or transitions, particularly involving reversals and releases

    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
    +0.29
    1.1%
    1499
    +0.10
    0.4%
    604
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.29
    0.06
    1287
    +0.10
    0.06
    919
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.52
     aquare
    -0.80
     Administrativna
    -0.73
     /**
    
    -0.67
     ló
    -0.65
     intersper
    -0.64
     biber
    -0.63
    
    
    -0.63
    ⓧ
    -0.63
     malin
    -0.62
    POSITIVE LOGITS
    Sklici
    1.01
    Glej
    0.83
     soulign
    0.82
     despotism
    0.80
    ołnier
    0.74
     împre
    0.70
    limsy
    0.69
    ',)
    0.69
     Jambi
    0.68
     sovere
    0.68
    Activations Density 0.496%

    No Known Activations