© 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. 600
    Prev
    Next
    INDEX
    Explanations

    numerical values or measures related to performance or statistics

    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
    +0.21
    1.0%
    1978
    +0.11
    0.5%
    31
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.21
    0.04
    1559
    +0.11
    0.04
    776
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.48
    ⓧ
    -0.84
     ProtoMessage
    -0.73
    Autoritní
    -0.71
    /***
    -0.67
    <tfoot>
    -0.67
    contentLoaded
    -0.66
    SequentialGroup
    -0.65
     Процитовано
    -0.64
    /**
    -0.63
    POSITIVE LOGITS
     territo
    1.22
     Minang
    1.21
     bandung
    1.20
     maroc
    1.19
     Meksi
    1.12
     Karang
    1.11
     saar
    1.10
     meis
    1.09
     magis
    1.09
     lele
    1.06
    Activations Density 0.062%

    No Known Activations