© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 552
    Prev
    Next
    INDEX
    Explanations

    elements related to user navigation and interactions within a web session, particularly focusing on paths taken from one page to another

    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
    184
    +0.36
    1.7%
    876
    +0.16
    0.8%
    50
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.36
    0.03
    876
    +0.16
    -0.01
    690
    +0.12
    0.02
    Negative Logits
    <bos>
    -3.71
    <?
    -1.30
    ⓧ
    -1.25
    
    
    -1.14
    /**
    -1.09
    <?
    
    -0.99
    /*
    -0.92
     Darío
    -0.84
    /***
    
    -0.81
     Mónica
    -0.78
    POSITIVE LOGITS
     stockholm
    1.14
     lele
    1.14
     pank
    1.14
     saha
    1.11
     kef
    1.10
     wien
    1.08
     magis
    1.06
     meis
    1.03
     lyon
    1.03
     kac
    1.02
    Activations Density 0.289%

    No Known Activations