© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14587
    Prev
    Next
    INDEX
    Explanations

    words related to the term "sur" in various texts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1983
    +0.15
    0.6%
    597
    +0.14
    0.5%
    1065
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.15
    0.02
    1065
    +0.14
    0.03
    1637
    +0.13
    0.02
    Negative Logits
    <bos>
    -0.49
     DbType
    -0.46
     Ton
    -0.43
     Bank
    -0.42
     Tony
    -0.42
    setLength
    -0.41
    లాలు
    -0.41
     Man
    -0.41
     Oslo
    -0.41
    QtWidgets
    -0.41
    POSITIVE LOGITS
     SUR
    1.21
    Sur
    1.15
     Sur
    1.12
    SUR
    1.09
    sur
    1.00
     sur
    0.95
     thuy
    0.89
     surfact
    0.88
     Surfer
    0.85
     lele
    0.83
    Activations Density 0.098%

    No Known Activations