© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 541
    Prev
    Next
    INDEX
    Explanations

    references to specific weeks or scheduling in a sports context

    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
    +0.13
    0.5%
    453
    +0.10
    0.4%
    1177
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1531
    +0.13
    0.04
    498
    +0.10
    0.04
    1502
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.88
    ⓧ
    -1.07
    
    -1.03
    <?
    -0.97
    /*
    -0.95
    /**
    -0.92
    <?
    -0.80
    /*++
    -0.71
    ,
    -0.66
     miesięcy
    -0.64
    POSITIVE LOGITS
     Græ
    1.45
     dises
    1.44
     Præ
    1.42
     hcm
    1.41
     Minang
    1.34
     salu
    1.32
     marte
    1.31
     socie
    1.30
     Kategor
    1.30
     kram
    1.30
    Activations Density 0.253%

    No Known Activations